paperclipai/paperclip
54.9
Adequate · 14 November 2026
1615.1k
lines of production code
TypeScript
with Rust
6
measurements over time
What this system is
Features
Add Hermes Gateway Smoke Test Container
A new Dockerfile and entrypoint script have been added to the \docker/hermes-gateway-smoke\ directory to support a smoke test environment for the Hermes gateway. The container is based on Node 24 and installs the \hermes-agent\ Python and npm packages at version 0.17.0. The entrypoint configures the API server (enabled on port 8642), generates or uses an API key, and executes the \hermes gateway run\ command with hook acceptance enabled.
docker/hermes-gateway-smoke · high confidence
Add KV Demo MCP Server fixture for local demonstrations
A new standalone demo package (\@paperclipai/kv-demo-mcp-server\) is introduced to showcase Paperclip's MCP integration. It provides a single-process server exposing four key/value MCP tools (\kv\_list\, \kv\_get\, \kv\_set\, \kv\_delete\) over Streamable HTTP, alongside a lightweight web UI that visualizes the in-memory store state in real-time. The tools are annotated with risk levels (read, write, destructive) to demonstrate Paperclip's policy enforcement and audit logging, with \kv\_delete\ specifically quarantined by default. The server supports optional token-based authentication via the \KV\_DEMO\_TOKEN\ environment variable and is designed for local development and demo scenarios. Also in this area: 2 commits (0 fixes) modifying packages/kv-demo-mcp-server.
packages/kv-demo-mcp-server · medium confidence · unverified
Add Paperclip assistant plugins for OpenAI and Claude
This change introduces a new set of assistant plugins that allow OpenAI (ChatGPT/Codex) and Claude models to connect to a user's Paperclip team via OAuth. The \integrations/assistant-plugins\ directory now contains build scripts and packaged plugins for both vendors, enabling assistants to review team status, delegate work to agents, and follow up on results using Paperclip's MCP endpoints. Users can now interact with their Paperclip workflows directly through these AI assistants, with the plugins handling authentication and tool exposure for tasks, agents, and documents.
integrations · high confidence
Add built-in Hermes Gateway adapter for remote agent connections
Introduces the \hermes\_gateway\ adapter, allowing Paperclip to connect to a remote Hermes Agent API server via HTTP/SSE instead of running a local child process. This new adapter supports session continuity through configurable \X-Hermes-Session-Key\ strategies (issue, agent, run, or none), enforces transport security by blocking remote plain HTTP by default (with a dev escape hatch), and includes a health-check environment test to validate connectivity. It also adds CLI output formatting for terminal display and fixes the extraction of real reasoning text from \reasoning.available\ gateway events.
packages/adapters/hermes/src · high confidence
Add native in-app announcements with persistent dismissal
The application now supports native in-app announcements that can be dismissed persistently. This change introduces the underlying data structure and example configurations for these announcements, including a staging preview and an animated example featuring a 'Plan, Build, Review' workflow visualization.
announcements · high confidence
Claude Local adapter UI configuration and transcript parsing
The Claude Local adapter now includes a new UI module that handles configuration building and stdout parsing. The \buildClaudeLocalConfig\ function constructs the adapter's runtime configuration, supporting explicit engine selection (CLI or ACP), environment variable bindings (including user-scoped secrets), and worktree workspace strategies. Additionally, the \parseClaudeStdoutLine\ function processes the adapter's output into structured transcript entries, correctly handling system initialization, assistant messages (including thinking blocks and tool calls), user messages, and result summaries with usage metrics. Tests verify that the configuration correctly omits the engine field when set to 'auto' to allow runtime fallback, while preserving explicit engine pins and user-scoped environment bindings.
packages/adapters/claude-local/src/ui · high confidence
Codex local adapter introduces ACP execution engine and device-login authentication
The Codex local adapter now supports the ACP execution engine as the default runtime, replacing the legacy CLI engine when environment constraints allow, and introduces a secure device-login flow that promotes credentials into company-scoped homes. This change adds structured stream event formatting for the CLI, robust quota classification that extracts retry times from provider limits, and a new auth precedence system that prioritizes configured API keys and host credentials over sandbox snapshots while warning when sandbox logins are shadowed.
packages/adapters/codex-local/src/server · high confidence
Codex-local adapter UI config builder and transcript parser
The codex-local adapter now includes a dedicated UI module that constructs adapter configuration objects and parses runtime stdout into transcript entries. The new build-config logic maps UI form fields (such as model, fast mode, engine selection, and sandbox bypass) into the specific settings expected by the Codex CLI and the experimental Paperclip Runner, while stripping unsupported keys and enforcing provider-specific constraints. The parse-stdout module translates raw Codex output lines into structured transcript entries, correctly handling tool calls, tool results, command executions, file changes, and reasoning blocks so that the UI can display accurate, human-readable run histories.
packages/adapters/codex-local/src/ui · high confidence
Cursor local adapter now supports remote sandbox and SSH execution
The Cursor local adapter has been extended to execute agent commands in remote environments, including both sandboxed runtimes and SSH-connected workspaces. Users can now run Cursor agents outside their local machine, with the adapter automatically resolving the correct agent binary (preferring \\~/.local/bin\ or \\~/.cursor/bin\), injecting Paperclip skills, and managing workspace synchronization. The adapter also includes a new environment testing flow that verifies command availability and authentication before execution, and robustly parses Cursor's JSONL output streams to surface session details, costs, and errors.
packages/adapters/cursor-local/src/server · high confidence
Documentation for new 1Password service-account connector and connection verification reports
Added documentation for the new 1Password service-account connector, detailing its setup via service account tokens, supported actions (vault listing, item management), and governance policies. Included verification reports for the aggregator routing logic, AgentMail, and AgentMail with Daytona sandbox, covering functional correctness, defect fixes, and live observations.
doc/connections · high confidence
Gemini Local adapter UI support for ACP engine and Gemini CLI v0.38 wire format
The Gemini Local adapter now includes UI-layer support for configuring and running the Gemini CLI via the ACP (Agent Control Protocol) engine, allowing users to pin the engine to 'acp' or 'cli' and configure specific ACP parameters like agent commands, modes, and permissions. Additionally, the adapter's stdout parser has been updated to handle the Gemini CLI v0.38 stream-json wire format, correctly interpreting new message structures, token usage statistics, and error states while maintaining backward compatibility with legacy formats.
packages/adapters/gemini-local/src/ui · high confidence
Initial CLI release with bundled build and changelog
The CLI package is now available as a standalone npm distribution, starting with version 0.3.1. This release introduces a new esbuild-based build process that bundles workspace packages into a single executable targeting Node 24, alongside a comprehensive CHANGELOG.md documenting the version history from 0.2.1 through 0.3.1 and a new README.md with updated documentation and links.
cli · high confidence
Initial release of the @paperclipai/db package with Drizzle ORM support
This change introduces the new \packages/db\ package, establishing the project's database layer using Drizzle ORM with a PostgreSQL dialect. It includes the core configuration files (\drizzle.config.ts\, \tsconfig.json\, \vitest.config.ts\) and a changelog tracking versions from 0.2.1 through 0.3.1. A key behavioral addition is the configuration of \.gitattributes\ to treat Drizzle migration snapshots as binary files, which prevents merge conflicts and reduces diff noise by disabling text-based merging and diffing for these generated files.
packages/db · high confidence
Interactive setup prompts for database, storage, secrets, and server configuration
The CLI now includes a new set of interactive configuration wizards in the \cli/src/prompts\ directory, guiding users through initial setup for database, storage, secrets, LLM, logging, and server settings. Users can choose between embedded PostgreSQL and external PostgreSQL for the database, select between local disk and S3-compatible storage, configure secret providers (local encrypted, AWS Secrets Manager, GCP Secret Manager, or HashiCorp Vault), and define server reachability modes (loopback, LAN, Tailnet, or custom) with specific authentication and exposure profiles. These prompts use the \@clack/prompts\ library to collect and validate user input, defaulting to recommended local configurations while allowing customization for production or multi-user environments.
cli/src/prompts · high confidence
Introduce Cursor Cloud adapter for remote agent execution
A new \cursor\_cloud\ adapter has been added to the \packages/adapters/cursor-cloud\ location, enabling Paperclip to run Cursor Cloud Agents through the official Cursor SDK. This adapter supports durable remote agent sessions that persist across Paperclip heartbeats, allowing Cursor to handle remote code execution while Paperclip retains task state. Users can configure the adapter with a Git repository URL, select a runtime environment (cloud, self-hosted pool, or named machine), and optionally enable features like auto-creating pull requests. The implementation includes CLI event formatting, server-side execution logic, session management, and environment validation to ensure proper authentication and configuration.
packages/adapters/cursor-cloud · high confidence
Introduce Cursor Local adapter UI and CLI formatting
Adds the user-facing interface for the new Cursor Local adapter, including CLI event formatting and UI stdout parsing. The CLI now displays structured run logs with color-coded user/assistant messages, thinking blocks, and tool calls/results. The UI parses the adapter's stdout into transcript entries, handling shell tool output truncation and error states, enabling users to view and interact with Cursor Local agent runs in the interface.
packages/adapters/cursor-local/src/ui · high confidence
Introduce Gemini CLI local adapter with ACP engine support
A new local adapter for the Gemini CLI is now available, allowing Paperclip to run Gemini locally on the host machine. The adapter defaults to the ACP engine (requiring Node 24+) for persistent, resumable sessions and skill injection, while also supporting a legacy CLI engine. It includes a comprehensive list of supported models (including Gemini 3.1 Pro, 3.8 Flash, and 2.5 Pro) and handles headless execution by suppressing browser auth prompts. The adapter automatically installs the \@google/gemini-cli\ package in its sandbox and injects local skills into \\~/.gemini/skills/\.
packages/adapters/gemini-local/src · high confidence
Introduce Kimi Code CLI local adapter with dual execution engines
Users can now run the Kimi Code CLI locally via a new \kimi\_local\ adapter that supports both the ACP (Agent Control Protocol) engine and a direct CLI engine. The adapter exposes several Kimi models (K2.8 Preview, K2.7 Coding Highspeed, K3, and K3 256K) and allows users to configure thinking effort levels (low, high, max) for compatible models. It handles session persistence by capturing and resuming session IDs, manages skill injection through a dedicated skills directory, and provides robust error handling for authentication, network issues, and session failures. The adapter defaults to the ACP engine but allows explicit selection of the CLI engine, with appropriate environment setup for headless execution. Also in this area: 4 commits (3 fixes) fixing packages/adapters; Claude and Codex model lists reordered; session resume preserves tool context.
packages/adapters/kimi-local/src · medium confidence · unverified
Introduce OpenClaw Gateway adapter UI configuration and log parsing
This change adds the UI-layer support for the new OpenClaw Gateway adapter, enabling users to configure and interact with OpenClaw-based agents. The \build-config.ts\ module constructs the gateway configuration object, applying safe defaults for timeouts (120s/120000ms) and identity (role: operator, scopes: operator.admin) while handling authentication tokens, device auth settings, and custom headers. The \parse-stdout.ts\ module implements log parsing to translate OpenClaw gateway output streams into structured transcript entries, distinguishing between assistant messages, errors, and lifecycle events. These components are exported via \index.ts\ to integrate with the broader adapter system.
packages/adapters/openclaw-gateway/src/ui · high confidence
Introduce OpenClaw Gateway adapter with CLI event formatting and stream normalization
The new openclaw-gateway adapter adds CLI capabilities for handling stream events. It includes a stream normalization utility that parses lines prefixed with 'stdout' or 'stderr' to distinguish output sources, and a CLI formatter that prints these events with color coding (cyan for debug events, blue for standard gateway events, gray for others) when debug mode is enabled, or plain text otherwise.
packages/adapters/openclaw-gateway/src/cli, packages/adapters/openclaw-gateway/src/shared · high confidence
Introduce OpenClaw Gateway adapter with WebSocket-based agent configuration
A new 'openclaw\_gateway' adapter has been added, enabling Paperclip to invoke OpenClaw via the Gateway WebSocket protocol rather than standard HTTP endpoints. This adapter supports native gateway authentication and connection semantics, allowing users to configure connection details such as the WebSocket URL, shared tokens, and client identity. It includes specific configuration options for session routing strategies, timeout handling, and automatic device pairing on first connect. The adapter also defines how wake payloads are structured, ensuring compatibility with the gateway agent schema by embedding Paperclip context in message text rather than sending unsupported root-level parameters.
packages/adapters/openclaw-gateway/src · high confidence
Introduce OpenCode local adapter UI parsing and configuration
The OpenCode local adapter now includes a UI integration layer that handles configuration building and stdout parsing. The new \build-config.ts\ module maps adapter settings (such as working directory, model, and environment bindings) into the specific format required by the OpenCode CLI, while \parse-stdout.ts\ implements a parser that converts OpenCode's JSON-based stdout stream into structured transcript entries, supporting assistant text, thinking/reasoning blocks, tool calls with results, and step completion metrics.
packages/adapters/opencode-local/src/ui · high confidence
Introduce OpenCode local adapter for local agent runtime
A new 'opencode\_local' adapter is added, allowing users to run the OpenCode CLI locally as the agent runtime. This adapter manages its own sandbox installation via a custom script to optimize for bandwidth-constrained environments and supports a wide range of models from providers like OpenAI, Anthropic, Google, and xAI. It enables provider/model routing, session resumption, and configurable permissions (including a headless-safe 'allow-all' mode), while explicitly preventing config file pollution in the workspace by disabling OpenCode's project config writing.
packages/adapters/opencode-local/src · high confidence
Introduce OpenCode local adapter with remote execution and environment-driven configuration
This change adds the \opencode-local\ adapter, enabling the system to execute AI tasks using the OpenCode runtime. It supports both local and remote (SSH) execution targets, including workspace preparation, skill injection, and environment syncing for remote runs. The adapter features a new CLI event formatter for structured JSONL output, robust model discovery with retry logic and caching, and environment-driven configuration via \PAPERCLIP\_OPENCODE\_PROVIDERS\ and \PAPERCLIP\_OPENCODE\_SMALL\_MODEL\ to support custom providers and cost optimization. It also includes a session codec for handling session persistence and a parser for OpenCode's JSONL stream to extract summaries, usage, and errors.
packages/adapters/opencode-local/src/server · high confidence
Introduce PR Gardening skill to maintain instance-authored pull requests
A new automated workflow has been added to actively manage pull requests opened by the Paperclip instance itself. The skill discovers candidates by scanning recent issues for PR mentions, then mechanically verifies their readiness by checking status checks, Greptile results, merge conflicts, and review decisions. It restricts its scope to the instance's own GitHub identity by default, excluding community contributions, and drives non-ready PRs toward a green state using the \/prepare-paperclip-pr\ skill without ever merging or approving them. The workflow includes safeguards against duplicate task creation, respects activity windows and cooldowns, and can optionally tidy the user's inbox by archiving originating issues once a PR is confirmed merged.
.agents/skills/pr-gardening · high confidence
Introduce Paperclip Eval Kernel for provider-neutral evaluation orchestration
A new workspace-private package, \@paperclipai/paperclip-eval-kernel\, provides a generic, deterministic matrix orchestration engine for evaluations. It allows consumers to define scenarios and candidates with execution and scoring callbacks, while enforcing fail-closed compatibility checks via a \preflight\ hook that validates against the Paperclip Runner. This separation keeps the runner package free of scenario corpus and provider configuration dependencies, while the \paperclip-runner\ package adds a browser-based devtool for live protocol replay and static fixture validation to aid in debugging and conformance testing. Also in this area: 6 commits (1 fix) modifying packages/paperclip-runner; 29 commits (25 fixes) fixing packages/paperclip-runner.
(repo-wide) · medium confidence · unverified
Introduce Pi Local adapter with remote execution and custom provider support
The new \pi-local\ adapter enables running the Pi coding agent locally or via remote SSH, including workspace preparation, skill synchronization, and session management. It supports custom LLM gateway routing through the \PAPERCLIP\_PI\_PROVIDERS\ environment variable, which allows injecting provider configurations into a managed \models.json\ file. The adapter also includes robust parsing of Pi's JSONL output for streaming text, tool execution, and usage/cost tracking, along with comprehensive tests for remote execution flows and model discovery.
packages/adapters/pi-local/src/server · high confidence
Introduce Pi-local adapter UI components for configuration and transcript parsing
This change adds the user-facing UI layer for the new pi-local adapter, including build configuration logic and a parser for the adapter's stdout stream. The configuration module maps environment bindings, model settings, and execution commands to the adapter's runtime requirements. The parser translates the Pi agent's JSON-based output into structured transcript entries, handling agent lifecycle events, streaming text and thinking content, and tool results (including extraction from array-formatted content and matching tool names).
packages/adapters/pi-local/src/ui · high confidence
Introduce agent-shim tool for sandboxed adapter execution
Added a new Go-based shim tool in the tools directory that reads a runtime command specification (JSON) and executes the specified adapter binary within the current process. This shim enables sandboxed execution of agent adapters by resolving the command path and replacing the shim process with the target adapter, allowing signals like SIGTERM to reach the adapter directly.
tools · high confidence
Introduce built-in grok\_local adapter with device-login authentication and streaming output formatting
The grok\_local adapter is now available as a built-in option, allowing Paperclip to run the native Grok Build CLI locally on the host machine. This update introduces a secure device-login flow that parses the Grok CLI's authorization prompt, validates the credentials, and promotes them to the company-scoped home directory. It also adds a streaming event formatter that displays real-time agent thoughts, assistant responses, and run completion status directly in the CLI. The adapter supports model-specific reasoning efforts (including xhigh for grok-4.7 and grok-4.6) and stages project skills and instructions into the execution workspace.
packages/adapters/grok-local · high confidence
Introduce immutable Daytona runner image with pinned agent CLIs and provider pack
The Daytona runner sandbox image is now built from a new Dockerfile that assembles a source-compiled \paperclip-runnerd\ binary and an immutable provider pack containing Node 24.21.0, OpenCode 1.18.34, ACPX 0.13.1, and several qualified agent CLIs. The image bundles specific versions of Grok (1.0.46), Gemini CLI (0.62.0), Kimi Code (2.1.1), Cursor (2026.10.01-e373342), and GitHub CLI (2.102.0), alongside Hermes (0.19.0). The build process enforces strict integrity by verifying the \pnpm-lock.yaml\ against a SHA-256 digest before installation and pins base images to manifest digests to ensure reproducible, tamper-resistant sandbox environments. Also in this area: 1 commit (0 fixes) modifying docker, patches, rules.
docker/daytona-runner · medium confidence · unverified
Introduce least-privilege Tailscale HTTPS broker for managed branch runtimes
A new dedicated Tailscale HTTPS broker service has been added to manage HTTPS-to-loopback listeners for managed branch runtimes, allowing the Paperclip app/agent to obtain automatic trusted HTTPS previews without requiring Tailscale operator authority. The broker enforces a strict least-privilege model by operating only on a dedicated port range, verifying that listeners are loopback-only and owned by the managed runtime via /proc, and using unguessable lease handles to ensure that only the originating runtime can remove its own listeners. It communicates with the Tailscale CLI via a serialized, fail-closed transaction core that protects the primary :443 route and supports operator-declared protected ports, while maintaining a bounded, append-only security audit log of all allow/deny decisions.
packages/tailscale-https-broker · high confidence
Introduce local Cursor adapter with sandbox support and auto-injected skills
A new local adapter for the Cursor Agent CLI has been added, enabling users to run Cursor locally as the agent runtime. This adapter handles installation via the official Cursor installer script and provides a comprehensive list of supported model IDs for fallback discovery. Key behavioral changes include piping prompts to Cursor via stdin, resuming chat sessions across heartbeats, and automatically injecting Paperclip local skills into the Cursor environment. The adapter also defaults to the '--yolo' execution flag and supports structured JSON stream output in run logs.
packages/adapters/cursor-local/src · high confidence
Introduce local Pi coding agent adapter
A new adapter for running the Pi AI coding agent locally has been added, allowing users to execute Pi as the agent runtime within Paperclip. This change enables provider/model routing in Pi format, supports session resumption across heartbeats, and provides access to Pi's built-in tool set (read, bash, edit, write, grep, find, ls). The adapter includes a specific sandbox installation command for the Pi coding agent and defines configuration options for working directories, instructions, prompts, and timeouts.
packages/adapters/pi-local/src · high confidence
Introduce managed CLI install, service lifecycle, and onboarding flow
The Paperclip CLI now supports a managed per-user installation model, allowing users to install, update, and uninstall the CLI via dedicated commands while preserving user data. An interactive onboarding wizard guides first-time setup, including the option to install and start a background service (managed via systemd or launchd) and automatically open the dashboard. The CLI also includes a doctor command for diagnostics, a test-drive command for isolated local testing, and telemetry tracking for installation and company import events.
cli/src · high confidence
Introduce paperclip-page skill for publishing static sites to S3/CloudFront
Added the \paperclip-page\ skill, which provides a secure helper script (\publish.sh\) and documentation for publishing static HTML directories to a dedicated Paperclip S3 bucket served via CloudFront. The skill enforces a strict security posture by scoping AWS credentials to the helper process only (using \PAPERCLIP\_PAGE\AWS\\*\ variables), rejecting symlinks and hidden files, and preventing destructive operations like \s3 sync --delete\. It includes a test suite (\publish.test.mjs\) validating credential scoping, slug validation, and dry-run behavior.
.agents/skills/paperclip-page · high confidence
Introduce sandbox duplex frame codec and bridge transport contract
The adapter-utils package now includes a versioned, newline-delimited JSON frame codec (v2) for the sandbox duplex channel, enforcing a 256 KB per-frame size limit to prevent oversized payloads. It also defines the shared bridge transport contract, including the \duplex\_channel\_lost\ error code, run disposition logic, and nested timeout budgets (30s forward, 32s response, 35s gateway wait), while providing a utility to identify safe HTTP methods for retryable operations.
packages/adapter-utils/src · high confidence
Introduce standalone Paperclip MCP server package
Adds a new \@paperclipai/mcp-server\ package that exposes the Paperclip REST API as a Model Context Protocol (MCP) server. The package provides a set of MCP tools for reading and writing issues, managing approvals, handling comments, and controlling issue workspace services, along with runtime-scoped tools for connection search and requests. It is configured via environment variables (\PAPERCLIP\_API\_URL\, \PAPERCLIP\_API\_KEY\, etc.) and can be run via \npx\ or locally from the built distribution.
packages/mcp-server · high confidence
Introduces isolated local state management and hardened configuration storage
The CLI now supports isolating local runtime state via the new --data-dir flag, which allows users to specify a custom directory for instance-specific data, configuration, and secrets. This change introduces a robust configuration store that automatically migrates legacy database settings (pglite to embedded-postgres), validates config schemas, and safely backs up invalid configurations. Additionally, the CLI now manages environment variables and secrets more securely by automatically generating and persisting JWT and tool-action signing secrets in a local .env file, and by auto-creating a local secrets encryption key file during onboarding when using the local\_encrypted provider.
cli/src/config · high confidence
Kitchen Sink plugin example added to demonstrate full plugin API surface
A new reference plugin example has been added to showcase the complete Paperclip plugin API, including UI slots (pages, settings, sidebar, widgets, annotations), runtime launchers, agent tools, scheduled jobs, webhooks, and local workspace command execution. The example includes a build script for the UI bundle and a comprehensive manifest defining capabilities, configuration options, and entry points. Also in this area: New plugin orchestration smoke example plugin; Add File Browser and Hello World example plugins; Add plugin orchestration smoke example.
packages/plugins/examples · high confidence
New ACP execution engine and authentication infrastructure for Claude Local adapter
The \claude-local\ adapter now includes a new ACP (Agent Client Protocol) execution engine alongside the existing CLI engine, allowing users to run Claude agents via the ACP runtime. This change introduces robust authentication handling, including a new \setup-token\ flow for OAuth login, environment probes to detect missing or invalid credentials, and specific error mapping for auth failures. It also adds quota management to classify provider limits and retry windows, and implements secure config seeding that sanitizes local-only settings for remote sandbox environments. Comprehensive test coverage and characterization fixtures validate the new login, quota, and config behaviors.
packages/adapters/claude-local/src/server · high confidence
New AI assistant skills for UI design and company management
Added new skill definitions to guide the AI assistant in consistent UI development and company creation workflows. The \design-guide\ skill provides a comprehensive reference for the Paperclip design system, including React 19/TypeScript/Vite tech stack details, OKLCH-based design tokens, typography scales, status/priority color systems, and a full inventory of shadcn/ui primitives and custom components (like EntityRow, StatusBadge, and Identity). The \company-creator\ skill and \paperclip\ symlink establish the structural context for generating and managing company-related UI elements.
.claude/skills · high confidence
New CLI authentication flow and context management
The CLI now supports a browser-based authentication flow for board access, introducing a new \board-auth.ts\ module that handles challenge creation, polling, and credential storage in a local JSON store. A new \context.ts\ module manages multi-profile configurations (supporting 'board' and 'agent' personas) with home-based defaults and ancestor-directory resolution. The HTTP client (\http.ts\) has been updated to include a \putRaw\ method for binary uploads and improved error handling with automatic token recovery on auth failures.
cli/src/client · high confidence
New CLI client command suite for access, adapters, agents, approvals, assets, auth, and company management
The CLI now includes a comprehensive set of new commands under \cli/src/commands/client/\ to manage core platform resources. Users can now inspect and manage access policies, invites, and join requests (\access\); install, update, and configure adapters (\adapter\); manage agent keys, skills, instructions, and sessions (\agent\); handle approval workflows (\approval\); upload and download company assets like images and logos (\asset\); authenticate via board or agent credentials (\auth\); and perform full company import/export, feedback trace management, and company profile operations (\company\). These commands provide programmatic access to the Paperclip API for automation and administration.
cli/src/commands/client · high confidence
New CLI commands for configuration, diagnostics, and release management
The CLI now includes several new commands to improve setup and maintenance: \paperclip configure\ allows interactive editing of config sections (database, LLM, server, etc.); \paperclip doctor\ runs a suite of health checks with optional repair; \paperclip channels\ displays current and available release channels (stable, beta, nightly, canary); \paperclip db:backup\ creates manual database backups with retention controls; \paperclip auth-bootstrap-ceo\ generates bootstrap CEO invites for authenticated deployments; \paperclip allowed-hostname\ manages allowed hostnames for private deployments; \paperclip env\ exports deployment environment variables; \paperclip env-lab\ manages SSH environment lab fixtures; and \paperclip heartbeat-run\ invokes agent heartbeats manually.
cli/src/commands · high confidence
New CLI tools for stream formatting and quota monitoring
The local Claude adapter now includes a new CLI module that formats Claude stream events for the terminal (coloring assistant text, tool calls, and errors) and provides a \quota-probe\ command to check usage limits via OAuth, CLI, or aggregated sources, outputting results in JSON or human-readable text.
packages/adapters/claude-local/src/cli · high confidence
New CLI utility modules for banner, networking, and path resolution
The CLI now includes a set of new utility modules in the utils directory to support core functionality. A new banner module displays the 'paperclip' ASCII art and updated tagline ('The app people use to manage AI agents for work') upon startup. Networking utilities have been added to check if a specific port is available and to construct local application and health-check URLs, handling host normalization (e.g., 0.0.0.0 to 127.0.0.1) and IPv6 formatting. Additionally, a path resolver utility helps locate runtime files by expanding home prefixes and searching through config, workspace, and current working directories.
cli/src/utils · high confidence
New OpenClaw smoke test harness for webhook validation
A new Docker-based smoke test service has been added to the \docker/openclaw-smoke\ directory to validate OpenClaw webhook integrations. The service, built on Node 24 Alpine, exposes a configurable webhook endpoint (defaulting to \/webhook\) that accepts POST requests, enforces optional authentication headers, and stores received events in memory for inspection via \/events\ and \/health\ endpoints. This tool allows users to quickly verify that webhook payloads are correctly formatted and received by the system during integration testing.
docker/openclaw-smoke · high confidence
New PR Report skill for generating maintainer-grade review artifacts
A new 'pr-report' skill has been added to the agent's capabilities, enabling it to produce detailed, maintainer-grade reports on pull requests or code contributions. This skill guides the agent to perform deep architectural and behavioral reviews, distinguishing between product scope and implementation quality, and to generate polished output artifacts. Users can now request deep PR reviews, design explanations, or merge recommendations, with the agent capable of producing standalone HTML reports (using a provided starter template and style guide) or Markdown summaries that follow an editorial, high-contrast visual design.
.agents/skills/pr-report · high confidence
New Workspace Changes tab for viewing Git diffs
A new "Workspace Changes" plugin adds a Changes tab to execution and project workspaces, allowing users to view Git diffs directly in the UI. The plugin computes diffs locally using the \@pierre/diffs\ library and exposes a React-based UI that supports staged, unstaged, head, and untracked views, with features like file sidebar filtering, copy-to-clipboard, and handling of binary/oversized files. It registers a \detailTab\ slot for \execution\_workspace\ and \project\_workspace\ entity types, backed by a worker that queries workspace metadata and applies path filters and output caps.
packages/plugins/plugin-workspace-diff · high confidence
New agent skills for email, complaints, and company governance
Agents now have access to new built-in skills that expand their capabilities: the AgentMail skill enables reading assigned email inboxes, sending replies, and checking delivery status; the Complain skill allows agents to autonomously submit unstructured feedback about their tooling or work experience; and the Paperclip Board skill guides agents through company onboarding, agent hiring with governance approvals, and board-level management tasks. These skills provide structured workflows and API references for email communication, internal feedback, and organizational administration.
skills · high confidence
New bundled skills for documentation, issue triage, agent coaching, and status summarization
The skills catalog now includes several new bundled capabilities: a doc-maintenance skill to detect and fix documentation drift against code changes; an issue-triage skill to automate inbox management and issue status updates; a reflection-coach skill to analyze agent execution records and propose evidence-backed instruction or skill improvements; a status-card-query skill to compile prose prompts into structured company-search queries and write summaries; a summarize-status skill to generate actionable, human-readable status summaries for projects and workspaces; a task-planning skill to break down issues into structured implementation plans with child tasks and blockers; and a paperclip-capsules skill with references for generating and validating agent capsule visuals and brand assets.
packages/skills-catalog · high confidence
New database maintenance scripts for session cleanup and bootstrap invites
Added two new CLI scripts to the database package: \clean-poisoned-claude-sessions.ts\ detects and helps resolve sessions where the Claude adapter's \previous\_message\_id\ was incorrectly set to a synthetic UUID (causing 400 errors on resume), and \create-auth-bootstrap-invite.ts\ generates a new bootstrap CEO invite token while revoking any existing active ones. These scripts provide operational tools for fixing stranded chat sessions and managing initial user access. Also in this area: 8 commits (2 fixes) modifying packages/db; 7 commits (4 fixes) fixing packages/db.
packages/db/scripts · medium confidence · unverified
New doctor checks validate configuration, dependencies, and runtime health
The CLI now includes a comprehensive set of pre-flight checks (accessible via the doctor command) that validate the environment before starting the server. These checks verify that the config file is valid, the database (PostgreSQL or embedded) is reachable and correctly configured, and that the required secrets (JWT, encryption keys, AWS credentials) are present and properly formatted. It also ensures the LLM API keys are functional, the server port is available, the log and storage directories are writable, and the Node.js runtime meets the minimum version. For managed installations, it verifies the integrity of the install store, shims, and PATH configuration, while also checking the status and health of background services.
cli/src/checks · high confidence
New garden-inbox skill for inbox cleanup
A new 'garden-inbox' skill has been added to scan a Paperclip user's Mine inbox, classify reversible archive candidates, request checkbox confirmation, and archive only accepted selections. The skill includes a bundled Node.js script (garden-inbox.mjs) and documentation (SKILL.md) that enforce a strict three-stage workflow: scan (read-only classification into buckets A–D), confirm (posting checkbox interactions on the driving issue), and apply (archiving only accepted options after user resolution). It handles safety constraints such as preserving declined candidates on reruns, respecting API row caps, and ensuring inbox archiving does not mutate underlying issues or workspaces.
.agents/skills/garden-inbox · high confidence
New inline AgentMail connection setup and unified credential fields
Users can now connect AgentMail directly from task intents via a new inline setup flow (AgentMailIntentSetup) that handles API key entry, credential selection, and inbox provisioning without leaving the chat context. This is supported by new reusable UI components: ApiKeyCredentialField for selecting or entering API keys, ConnectionChoiceList for account selection, and ConnectionInstructions for managing agent-specific instructions. The change also introduces ConnectionIntentInteractionBody to orchestrate these connection intents within tasks, ensuring a consistent setup experience across the app.
ui/src/features/connections · high confidence
New isolated container environment for untrusted PR reviews
A new Docker-based setup is introduced in the docker/untrusted-review directory to enable reviewing untrusted pull requests in isolated containers. The Dockerfile provisions a Node 24 environment with essential CLI tools (git, gh, jq, ripgrep, etc.) and pre-installs AI coding assistants (Claude Code, Codex). It includes a helper script, review-checkout-pr, which automates cloning a repository and checking out a specific PR into a detached worktree, facilitating safe, isolated code review workflows.
docker/untrusted-review · high confidence
New portable verification skill for Paperclip with automated onboarding smoke tests
A new \verify-paperclip\ agent skill has been introduced to standardize how Paperclip is verified across source checkouts, published npm packages, and hosted environments. The skill provides a structured workflow for selecting verification targets (local, staging, production) and driving real UI or CLI journeys. It includes new Python and Node.js helper scripts: \launch.py\ for starting isolated, credential-free local instances with embedded PostgreSQL; \doctor.py\ for read-only health and ownership checks; \stop.py\ for safe cleanup; and \onboarding-smoke.mjs\ for automated Playwright-based verification of the company creation and onboarding resumption flow. The skill also adds reference documentation for hosted QA account handling, npm installation verification, and checkout/data modes, along with unit tests to ensure the helpers cannot accidentally take ownership of or interfere with foreign checkouts.
.agents/skills/verify-paperclip · high confidence
New scaffolding tool for creating Paperclip plugins
A new CLI tool (\@paperclipai/create-paperclip-plugin\) is introduced to help developers quickly generate new Paperclip plugin projects. It scaffolds a complete starter structure including a typed manifest, worker entrypoint, example UI widget, and test files, supporting multiple templates (default, connector, workspace, environment) and categories. The tool provides a local development workflow with hot-reload capabilities and handles SDK dependency management for both internal workspace and external local development scenarios.
packages/plugins/create-paperclip-plugin · high confidence
New scripts for release automation, security validation, and testing
This change introduces a suite of new scripts in the \scripts/\ directory to support the release pipeline, improve security, and enhance testing. It adds \bootstrap-npm-package.mjs\ to create placeholder npm packages for trusted publishing, \build-npm.sh\ to bundle the CLI, and \build-standalone-public-packages.mjs\ to build isolated public packages. Security is strengthened with \app-brand-validation.mjs\ to validate SVG/PNG assets and \assert-cloud-image-sentry.mjs\ to verify container integrity. Operational reliability is improved with \assert-orphan-reaping.sh\ to prevent zombie processes in containers, \backup-db.sh\ for database backups, and \backfill-issue-reference-mentions.ts\ for data maintenance. Additionally, new test files like \acpx-patch-packaging.test.mjs\ and \app-brand-validation.test.mjs\ ensure the correctness of these new capabilities. Also in this area: 18 commits (4 fixes) modifying scripts; 1 commit (0 fixes) modifying scripts/ci-profile; 7 commits (1 fix) modifying scripts; Update PI agent profile to version 29 with new command digest; New E2E schedule monitor and 1Password, Supabase, Vercel connection definitions; and 8 more.
scripts · medium confidence · unverified
OpenClaw Gateway adapter server-side execution and testing logic
The OpenClaw Gateway adapter now includes the core server-side execution logic and its test suite. This adds the \execute\ function that manages WebSocket connections to the gateway, handles session key resolution (supporting run, issue, and fixed strategies), and constructs agent wake payloads while stripping root-level paperclip parameters. It also introduces environment testing capabilities via \testEnvironment\ to probe gateway connectivity and authentication, along with comprehensive unit tests for session key routing, parameter building, and dispatch boundary behavior.
packages/adapters/openclaw-gateway/src/server · high confidence
Paperclip core skill beta release added
A new beta release for the core Paperclip skill is now available in the skills-releases directory. This release includes the v0 snapshot of the skill's documentation, API reference, and helper scripts, along with a v7-roster historical release. Users can now access the Paperclip skill's core functionality and documentation through this new beta release.
skills-releases · high confidence
Published architecture and implementation plans for native chat adapters
This change adds the foundational design documentation for the native chat-adapters subsystem, detailing how Paperclip agents will integrate with external platforms like Slack, Microsoft Teams, Discord, Telegram, and GitHub. The files define the core architecture, including a registry-driven adapter model, a 'one bot per agent' identity strategy, and specific persistence schemas for endpoints, conversations, and deliveries. The package also includes research notes on leveraging the Vercel Chat SDK and OpenTag patterns, a comprehensive UI surface specification for the connection wizard and endpoint management tabs, and a live browser E2E runbook to qualify the adapters against real provider APIs.
doc/plans/chat-adapters · high confidence
Behavioural changes
1 commit (0 fixes) modifying docker/runner-image
A change to existing behaviour in docker/runner-image — 1 commit, 1 file: “feat(docker): build and check the Runner alone as the runner-artifacts target (\#21204)” (refs \#21204).
docker/runner-image · medium confidence · unverified
1 commit (0 fixes) modifying packages/paperclip-runner/examples, packages/paperclip-runner/src/scenarios, packages/paperclip-runner/src/standalone
A change to existing behaviour in packages/paperclip-runner/examples, packages/paperclip-runner/src/scenarios, packages/paperclip-runner/src/standalone — 1 commit, 53 files: “feat(runner): add SDK and developer tooling (\#12608)” (refs \#12608).
packages/paperclip-runner/examples, packages/paperclip-runner/src/scenarios, packages/paperclip-runner/src/standalone · medium confidence · unverified
10 commits (1 fix) modifying packages/paperclip-runner/src/evals
A change to existing behaviour in packages/paperclip-runner/src/evals — 10 commits (1 fix), 12 files: “feat(runner): add offline evaluation tooling (\#12653)”; “test(runner): add full-stack acceptance and eval gates (\#12700)”; “feat(runner): add guarded API search and call fallback (\#13003)”; and 7 more (refs \#12653, \#12700, \#13003, \#19488, \#18839, …).
packages/paperclip-runner/src/evals · medium confidence · unverified
10 commits (3 fixes) modifying packages/paperclip-runner/src/generated
A change to existing behaviour in packages/paperclip-runner/src/generated — 10 commits (3 fixs), 1 file: “fix(chat): resolve approvals and preserve unanswered questions (\#14613)”; “feat(cases): add persistent workflows with same-task agent handoffs (\#16959)”; “feat(runner): add SDK and developer tooling (\#12608)”; and 7 more (refs \#14613, \#16959, \#12608, \#13317, \#13038, …).
packages/paperclip-runner/src/generated · medium confidence · unverified
11 commits (3 fixes) modifying packages/paperclip-runner/src/drivers/dot
A change to existing behaviour in packages/paperclip-runner/src/drivers/dot — 11 commits (3 fixs), 5 files: “feat(runner): recover controller authority without interrupting execution (\#17097)”; “fix(runner): report Runner disconnect age when a Dot bridge exits (\#16296)”; “feat(dot): add guided invitations and persistent agent connections (\#15581)”; and 8 more (refs \#17097, \#16296, \#15581, \#16444, \#16305, …).
packages/paperclip-runner/src/drivers/dot · medium confidence · unverified
124 commits (45 fixes) modifying packages/paperclip-runner
A change to existing behaviour in packages/paperclip-runner — 124 commits (45 fixs), 32 files: “Fix isolated ACPX admission for assigned PRP tools (\#17149)”; “Extract Runner provider launch preparation (\#16977)”; “perf(runner): preload essential Claude task tools (\#16885)”; and 121 more (refs \#17149, \#16977, \#16885, \#18187, \#17097, …).
packages/paperclip-runner · medium confidence · unverified
14 commits (4 fixes) modifying server/src/modules/external-agents
A change to existing behaviour in server/src/modules/external-agents — 14 commits (4 fixs), 18 files: “refactor(accounting): remove company serialization from paid settlement (\#18917)”; “Share the external Runner lifecycle and add strict Muse contracts (\#16444)”; “perf(budgets): scope accounting and deliver enforcement asynchronously (\#17046)”; and 11 more (refs \#18917, \#16444, \#17046, \#19819, \#19750, …).
server/src/modules/external-agents · medium confidence · unverified
140 commits (64 fixes) modifying packages/plugins/sandbox-providers
A change to existing behaviour in packages/plugins/sandbox-providers — 140 commits (64 fixs), 189 files: “fix(daytona): keep the provider auto-stop strictly after the warm runner idle window (\#19199)”; “feat(plugin-kubernetes): self-hostable Kubernetes sandbox provider (stage 1/3: plugin package) (\#5790)”; “fix(runner): install verified API artifacts in execution workspaces (\#18494)”; and 137 more (refs \#19199, \#5790, \#18494, \#5580, \#20212, …).
packages/plugins/sandbox-providers · medium confidence · unverified
15 commits (2 fixes) modifying rules
A change to existing behaviour in rules — 15 commits (2 fixs), 16 files: “docs: require sleep-aware background work in reviews (\#17138)”; “docs: preserve runtime and verification lessons (\#16379)”; “docs: define module ownership and shared change review (\#17087)”; and 12 more (refs \#17138, \#16379, \#17087, \#16172, \#19380, …).
rules · medium confidence · unverified
159 commits (42 fixes) modifying packages/plugins/sdk
A change to existing behaviour in packages/plugins/sdk — 159 commits (42 fixs), 62 files: “Connect native Runner admission to plugin-owned workspaces (\#16978)”; “\[codex\] Add LLM Wiki plugin host support (\#5597)”; “feat(adapter-utils): provider-delegable syncIn seam with ordered post-upload commands (\#10340)”; and 156 more (refs \#16978, \#5597, \#10340, \#6009, \#5865, …).
packages/plugins/sdk · medium confidence · unverified
2 commits (0 fixes) modifying .agents/skills/directions-lab
A change to existing behaviour in .agents/skills/directions-lab — 2 commits, 70 files: “feat(ui): turn Artifacts V1 on for every instance and hide its toggle (\#19164)”; “feat(skills): add the directions-lab skill and its lab generator (\#17437)” (refs \#19164, \#17437).
.agents/skills/directions-lab · medium confidence · unverified
2 commits (1 fix) modifying packages/paperclip-runner/src/browser, packages/paperclip-runner/src/devtools, packages/paperclip-runner/src/react
A change to existing behaviour in packages/paperclip-runner/src/browser, packages/paperclip-runner/src/devtools, packages/paperclip-runner/src/react — 2 commits (1 fix), 31 files: “feat(runner): add SDK and developer tooling (\#12608)”; “fix(build): typecheck package, Playwright, and e2e test files in CI (\#18839)” (refs \#12608, \#18839).
packages/paperclip-runner/src/browser, packages/paperclip-runner/src/devtools, packages/paperclip-runner/src/react · medium confidence · unverified
2 commits (1 fix) modifying server/src/modules/execution-admission
A change to existing behaviour in server/src/modules/execution-admission — 2 commits (1 fix), 9 files: “fix(execution-admission): keep admitted project sets after settlement (\#18871)”; “feat(execution-admission): add project concurrency policy and admission storage (\#18746)” (refs \#18871, \#18746).
server/src/modules/execution-admission · medium confidence · unverified
21 commits (4 fixes) modifying packages/paperclip-runner/src/eval
A change to existing behaviour in packages/paperclip-runner/src/eval — 21 commits (4 fixs), 22 files: “feat: let agents name prompt-only tasks (\#14761)”; “feat(codex): default Codex to gpt-6.1-sol, half the gpt-5.6-sol price (\#19623)”; “feat(cases): add reusable prompt workflows (\#17114)”; and 18 more (refs \#14761, \#19623, \#17114, \#14420, \#16959, …).
packages/paperclip-runner/src/eval · medium confidence · unverified
242 commits (105 fixes) modifying packages/db/src
A change to existing behaviour in packages/db/src — 242 commits (105 fixs), 108 files: “feat(server): support volume-free web server handoff (\#18518)”; “\[codex\] Add LLM Wiki plugin host support (\#5597)”; “perf(db): index pending budget Stops instead of scanning all run results (\#20391)”; and 239 more (refs \#18518, \#5597, \#20391, \#12956, \#12335, …).
packages/db/src · medium confidence · unverified
3 commits (1 fix) modifying doc/benchmarks
A change to existing behaviour in doc/benchmarks — 3 commits (1 fix), 5 files: “refactor(perf): reuse database test setup for profile benchmark (\#18683)”; “fix(tool-gateway): bound MCP discovery memory and concurrency (\#14864)”; “perf(recovery): project current wait facts during action reconciliation (\#18793)” (refs \#18683, \#14864, \#18793).
doc/benchmarks · medium confidence · unverified
31 commits (4 fixes) modifying packages/paperclip-runner/src/protocol/generated
A change to existing behaviour in packages/paperclip-runner/src/protocol/generated — 31 commits (4 fixs), 2 files: “feat(prp): declare the contract for provider-started turns (\#21422)”; “feat(runner): project durable ACPX events (\#12424)”; “feat(task-chat): show Claude subagents as a collapsible tree in the runner turn (\#19264)”; and 28 more (refs \#21422, \#12424, \#19264, \#19291, \#14430, …).
packages/paperclip-runner/src/protocol/generated · medium confidence · unverified
335 commits (93 fixes) modifying (repo-wide)
A change to existing behaviour in (repo-wide) — 335 commits (93 fixs), 22 files: “\[codex\] Add LLM Wiki plugin host support (\#5597)”; “fix: make keyboard shortcut enablement a personal preference (\#14141)”; “ci: keep traceability regression tests in the Docker build context (\#12858)”; and 330 more (refs \#5597, \#14141, \#12858, \#12249, \#16885, …).
(repo-wide) · low confidence · unverified
357 commits (97 fixes) modifying packages/db/src/schema
A change to existing behaviour in packages/db/src/schema — 357 commits (97 fixs), 189 files: “fix: keep stale pending restore points from blocking retries (\#17344)”; “feat(server): support volume-free web server handoff (\#18518)”; “perf(db): index pending budget Stops instead of scanning all run results (\#20391)”; and 354 more (refs \#17344, \#18518, \#20391, \#14761, \#14141, …).
packages/db/src/schema · medium confidence · unverified
359 commits (103 fixes) modifying packages/db/src/migrations
A change to existing behaviour in packages/db/src/migrations — 359 commits (103 fixs), 484 files: “fix: keep stale pending restore points from blocking retries (\#17344)”; “feat(server): support volume-free web server handoff (\#18518)”; “perf(db): index pending budget Stops instead of scanning all run results (\#20391)”; and 356 more (refs \#17344, \#18518, \#20391, \#14761, \#14141, …).
packages/db/src/migrations · medium confidence · unverified
37 commits (13 fixes) modifying ui/src/pages/apps/chat
A change to existing behaviour in ui/src/pages/apps/chat — 37 commits (13 fixs), 53 files: “feat(connections): complete saved setup guidance and coverage maps (\#17739)”; “test: retire redundant suites and consolidate owner coverage (\#15978)”; “feat(connections): add AgentMail inboxes and email tasks (\#13256)”; and 34 more (refs \#17739, \#15978, \#13256, \#15728, \#14750, …).
ui/src/pages/apps/chat · medium confidence · unverified
37 commits (15 fixes) modifying server/src/modules/agent-lifecycle
A change to existing behaviour in server/src/modules/agent-lifecycle — 37 commits (15 fixs), 24 files: “Pause agents automatically when moving to a plugin environment (\#20375)”; “fix(cursor-cloud): support API-only controllers on managed stacks (\#18310)”; “fix(agents): report actionable lifecycle failure steps (\#16418)”; and 34 more (refs \#20375, \#18310, \#16418, \#20384, \#15631, …).
server/src/modules/agent-lifecycle · medium confidence · unverified
4 commits (2 fixes) modifying packages/paperclip-runner/src/drivers/cursor-cloud
A change to existing behaviour in packages/paperclip-runner/src/drivers/cursor-cloud — 4 commits (2 fixs), 16 files: “fix(runner): accept object fields sent as JSON text and name wrong-type rejections (\#21485)”; “feat(runner): add experimental Cursor Cloud provider (\#18068)”; “fix(build): typecheck package, Playwright, and e2e test files in CI (\#18839)”; and 1 more (refs \#21485, \#18068, \#18839, \#18782).
packages/paperclip-runner/src/drivers/cursor-cloud · medium confidence · unverified
4 commits (2 fixes) modifying packages/teams-catalog
A change to existing behaviour in packages/teams-catalog — 4 commits (2 fixs), 38 files: “feat(ui): add Speko voice setup, task calls, and Storybook coverage (\#15728)”; “fix(agents): reduce hiring templates to role descriptions (\#14985)”; “fix: stop prompts from encouraging subtasks (\#20362)”; and 1 more (refs \#15728, \#14985, \#20362, \#7550).
packages/teams-catalog · medium confidence · unverified
413 commits (160 fixes) modifying doc/plans
A change to existing behaviour in doc/plans — 413 commits (160 fixs), 394 files: “feat(server): support volume-free web server handoff (\#18518)”; “\[codex\] Add LLM Wiki plugin host support (\#5597)”; “fix(server): keep controller identity independent of Git probes (\#18649)”; and 408 more (refs \#18518, \#5597, \#18649, \#19946, \#21418, …).
doc/plans · medium confidence · unverified
5 commits (0 fixes) modifying packages/paperclip-runner/src/test-support
A change to existing behaviour in packages/paperclip-runner/src/test-support — 5 commits, 7 files: “refactor(acpx-sidecar): extract the runtime event step and the test process helper (\#21419)”; “Keep ACPX output while Core reconnects (\#19365)”; “test(runner): own Node executable in ACPX recovery fixtures (\#18196)”; and 2 more (refs \#21419, \#19365, \#18196, \#21421, \#21316).
packages/paperclip-runner/src/test-support · medium confidence · unverified
6 commits (2 fixes) modifying packages/paperclip-runner/test-fixtures
A change to existing behaviour in packages/paperclip-runner/test-fixtures — 6 commits (2 fixs), 41 files: “feat(task-chat): show hook and auto-review decisions as governance rows (\#19266)”; “feat(runner): add SDK and developer tooling (\#12608)”; “feat: integrate Pi 1.0 into the experimental Runner (\#14921)”; and 3 more (refs \#19266, \#12608, \#14921, \#18325, \#18028, …).
packages/paperclip-runner/test-fixtures · medium confidence · unverified
8 commits (1 fix) modifying packages/paperclip-runner/devtools
A change to existing behaviour in packages/paperclip-runner/devtools — 8 commits (1 fix), 59 files: “feat(codex): default Codex to gpt-6.1-sol, half the gpt-5.6-sol price (\#19623)”; “feat(runner): add rich ACP transport and durable interaction foundation (\#14430)”; “fix(evals): make the chat viewer the default published Evalbook (\#12952)”; and 5 more (refs \#19623, \#14430, \#12952, \#12608, \#14921, …).
packages/paperclip-runner/devtools · medium confidence · unverified
94 commits (43 fixes) modifying packages/paperclip-runner/src/cli
A change to existing behaviour in packages/paperclip-runner/src/cli — 94 commits (43 fixs), 62 files: “Fix isolated ACPX admission for assigned PRP tools (\#17149)”; “Connect TestOps protocol plans to verified GitHub attempts (\#18985)”; “Add explicit native tracing to the Runner eval CLI (\#17483)”; and 91 more (refs \#17149, \#18985, \#17483, \#21419, \#17962, …).
packages/paperclip-runner/src/cli · medium confidence · unverified
95 commits (43 fixes) modifying packages/paperclip-runner/src/control-plane
A change to existing behaviour in packages/paperclip-runner/src/control-plane — 95 commits (43 fixs), 13 files: “Add explicit Runner session release and resume support (\#19683)”; “Retain passive Codex output while Core reconnects (\#19029)”; “feat(runner): recover controller authority without interrupting execution (\#17097)”; and 92 more (refs \#19683, \#19029, \#17097, \#12638, \#21311, …).
packages/paperclip-runner/src/control-plane · medium confidence · unverified
ACP engine CLI output formatting and session resume behavior
The ACP engine now provides structured, color-coded CLI output for streaming events (sessions, text, tool calls, results, errors) via the new \printAcpxStreamEvent\ utility, and enforces safe session continuation when an operator stops a run: the engine verifies the ACP process can be stopped and preserves the session state to allow a follow-up run to resume from the interrupted checkpoint rather than starting fresh. Also in this area: 9 commits (4 fixes) modifying packages/adapter-utils; 2 commits (1 fix) modifying packages/adapter-utils; Agents receive concise identity and connection guidance instead of generic execution contracts; Improved adapter execution diagnostics, sandbox bridge timeouts, and session resume reliability.
packages/adapter-utils/src/acpx-engine · medium confidence · unverified
Codex local adapter model metadata, reasoning efforts, and fast mode support
The codex-local adapter now explicitly advertises current Codex-capable OpenAI models (including gpt-6-astra, gpt-6-sol, gpt-6-luna, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-5.4, gpt-5.4-mini, gpt-5, o3, o4-mini, gpt-5-mini, gpt-5-nano, o3-mini, and codex-mini-latest) with the default set to gpt-5.6-sol. It introduces reasoning effort controls (low, medium, high, xhigh, max, ultra) tailored to specific models, supports Fast mode for GPT-6 and GPT-5.6 families, and normalizes legacy model aliases like gpt-5.6 to gpt-5.6-sol to prevent CLI warnings.
packages/adapters/codex-local/src · high confidence
Default model set to Claude Opus 5 with expanded reasoning controls and new model support
The local Claude adapter now defaults to the Claude Opus 5 model when no model is explicitly configured, while preserving any explicit model IDs or environment overrides. The adapter introduces granular reasoning effort controls (low, medium, high, xhigh, max) tailored to specific models, with Opus 5, Sonnet 5, and Fable 5.1 supporting the full range. The model selector has been updated to include Claude Opus 5.5, Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 5, Sonnet 4.6, Sonnet 4.5, Fable 5.1, Fable 5, Mythos 5, and Haiku 4.5. Additionally, the adapter now supports ACP as the default engine, with specific configuration options for ACP session modes and state directories, and enforces Node 24+ for ACP runs.
packages/adapters/claude-local/src · high confidence
Expanded Docker deployment options and hardened process management
The Docker configuration has been reorganized into the \docker/\ directory and expanded to support multiple deployment targets, including AWS ECS Fargate (with a new task definition and environment example), systemd/quadlet integration, and a dedicated smoke-test container. The main server image now enforces Node 24 and uses \tini\ as PID 1 to ensure orphaned agent processes are reaped, with a \pids\_limit\ of 2048 as a safety backstop. Additionally, the quickstart and review environments now explicitly pass \PAPERCLIP\_ALLOWED\_HOSTNAMES\ and other deployment settings, and the main compose file enforces database health checks before starting the server.
docker · high confidence
Gemini Local adapter now defaults to the ACP execution engine
The Gemini Local adapter has shifted its default execution engine from the legacy CLI mode to the ACP (Agent Control Protocol) engine. This change introduces a new configuration option allowing users to explicitly select between 'ACP' and 'CLI' modes, with ACP enabled by default. The ACP engine brings support for persistent sessions, configurable permission modes, and remote execution via SSH and sandboxed environments. To ensure compatibility, the adapter now enforces a minimum Node.js version (24.11.0) for ACP runs and provides clear diagnostic feedback if the engine is unavailable, rather than silently falling back or failing.
packages/adapters/gemini-local/src/server · high confidence
Introduce Hermes adapter compatibility shim and task bridge skill
The \@paperclipai/adapter-hermes-gateway\ package is now a deprecated compatibility shim that forwards exports to the unified \@paperclipai/hermes-paperclip-adapter\, allowing existing plugin installs to continue working during a migration window. Additionally, a new \paperclip-task-bridge\ skill has been added to Hermes, enabling agents to create, update, and list Paperclip tasks using scoped API credentials, supported by new publish/restore scripts to manage workspace dependency resolution.
packages/adapters/hermes-gateway, packages/adapters/hermes/scripts, packages/adapters/hermes/skills · high confidence
Introduce sandboxed agent-runtime Docker images with Node 24 base
The docker/agent-runtime directory now provides a family of container images designed for running coding-agent harnesses in sandboxed environments. A new base image (agent-runtime-base) establishes the runtime foundation using Ubuntu 22.04, Node.js 24, and the paperclip-agent-shim, while also including ripgrep to prevent runtime dependency downloads. Derived images for specific agents—Claude, Codex, Gemini, OpenCode, Pi, and a stub for Hermes—extend this base by installing their respective CLI tools and configuring necessary settings (such as headless authentication for Gemini). This change shifts the execution model to use these dedicated, non-root images for sandboxed agent runs.
docker/agent-runtime · high confidence
New shared validation and eligibility logic for agents and account handles
The shared package introduces new TypeScript modules and tests that enforce stricter validation and eligibility rules for agents and account handles. \account-handle.ts\ and its tests define a \toAccountHandle\ function that rejects identifiers containing whitespace, special characters, or shell metacharacters, ensuring safe directory and secret naming. \agent-eligibility.ts\ and its tests implement org-chain health checks, blocking work assignment and invocation for agents with terminated ancestors, missing managers, or reporting cycles, while warning about paused managers. Additionally, \agent-appearance.ts\ standardizes agent avatar palettes and states, and \adapter-auth-check-code.ts\ provides a stable constant for adapter authentication status checks. Also in this area: 4 commits (2 fixes) modifying packages/shared/src; 7 commits (1 fix) modifying packages/shared/src; 5 commits (4 fixes) fixing packages/shared/src/types; New type definition for recent issue comments; Agent runner qualification, project access, and configuration warning support; and 11 more.
packages/shared · medium confidence · unverified
Standardized CLI adapter registry with HTTP and process fallbacks
The CLI now uses a centralized adapter registry to manage output formatting for various AI providers. This change introduces two new generic adapter types, \http\ and \process\, which handle standard output events by printing trimmed lines to the console. These serve as the default fallback behavior when a specific provider adapter is not found or selected. The registry also consolidates the existing provider-specific adapters (including Claude, Codex, Cursor, Gemini, Grok, Kimi, Hermes, OpenCode, Pi, and OpenClaw) into a single lookup mechanism, ensuring consistent event handling across all supported integrations.
cli/src/adapters · high confidence
Fixes
11 commits (6 fixes) fixing packages/paperclip-runner/scripts/controlled-evals
A fix in packages/paperclip-runner/scripts/controlled-evals — 11 commits (6 fixs), 17 files: “fix(evals): share bounded request policy with qualification (\#17765)”; “fix(evals): qualify Runner model receipts with separate operating reconciliation (\#17929)”; “feat(evals): enforce fixed Runner request allocations (\#17452)”; and 8 more (refs \#17765, \#17929, \#17452, \#17469, \#17523, …).
packages/paperclip-runner/scripts/controlled-evals · medium confidence · unverified
159 commits (87 fixes) fixing packages/paperclip-runner/src
A fix in packages/paperclip-runner/src — 159 commits (87 fixs), 25 files: “feat(chaos): add the on-demand crash-point suite and its manual CI workflow (\#19946)”; “Bound native OpenCode assigned-tool catalog projection (\#17740)”; “feat(runner): add Codex session driver (\#12371)”; and 156 more (refs \#19946, \#17740, \#12371, \#21328, \#17097, …).
packages/paperclip-runner/src · medium confidence · unverified
214 commits (131 fixes) fixing packages/paperclip-runner/src/live
A fix in packages/paperclip-runner/src/live — 214 commits (131 fixs), 104 files: “fix(native): bound an idle warm local runner whose controller died (\#19879)”; “Add explicit Runner session release and resume support (\#19683)”; “fix(runner): bind Cursor sidecars to the runner package, not the workspace root (\#19255)”; and 211 more (refs \#19879, \#19683, \#19255, \#16977, \#17740, …).
packages/paperclip-runner/src/live · medium confidence · unverified
275 commits (140 fixes) fixing packages/paperclip-runner/runner/crates/runner-core
A fix in packages/paperclip-runner/runner/crates/runner-core — 275 commits (140 fixs), 112 files: “Fix isolated ACPX admission for assigned PRP tools (\#17149)”; “feat: let agents name prompt-only tasks (\#14761)”; “test(runner): bound Codex provider event waits by a hang ceiling, not 5s (\#19306)”; and 272 more (refs \#17149, \#14761, \#19306, \#16977, \#16885, …).
packages/paperclip-runner/runner/crates/runner-core · medium confidence · unverified
3 commits (2 fixes) fixing cli/src/services
A fix in cli/src/services — 3 commits (2 fixs), 1 file: “fix(cli): add KillMode=mixed to generated systemd unit (\#18598)”; “fix(cli): materialize the managed install before the onboarding service install (\#12148)”; “feat(cli): add managed install, update, and service lifecycle (\#10045)” (refs \#18598, \#12148, \#10045).
cli/src/services · medium confidence · unverified
3 commits (2 fixes) fixing packages/paperclip-runner/scripts/contracts
A fix in packages/paperclip-runner/scripts/contracts — 3 commits (2 fixs), 2 files: “fix(runner): attest upstream releases and bind ACPX uniformly for every harness (\#18325)”; “fix(runner): reuse image packs only with matching contract digest (\#18237)”; “feat(runner): upgrade ACPX to 0.22.0 and move patched behavior into Paperclip (\#20770)” (refs \#18325, \#18237, \#20770).
packages/paperclip-runner/scripts/contracts · medium confidence · unverified
4024 commits (2210 fixes) fixing server
A fix in server — 4024 commits (2210 fixs), 4476 files: “fix: keep stale pending restore points from blocking retries (\#17344)”; “fix(issues): finish a reassignment whose native stop settles after the request (\#19354)”; “Connect native Runner admission to plugin-owned workspaces (\#16978)”; and 4016 more (refs \#17344, \#19354, \#16978, \#11200, \#18518, …).
server · medium confidence · unverified
42 commits (23 fixes) fixing packages/paperclip-runner/src/drivers
A fix in packages/paperclip-runner/src/drivers — 42 commits (23 fixs), 32 files: “Fix isolated ACPX admission for assigned PRP tools (\#17149)”; “perf(runner): preload essential Claude task tools (\#16885)”; “refactor(runner): remove the direct assigned-gateway path (\#21311)”; and 39 more (refs \#17149, \#16885, \#21311, \#13005, \#17725, …).
packages/paperclip-runner/src/drivers · medium confidence · unverified
50 commits (27 fixes) fixing packages/paperclip-runner/src/protocol-actions
A fix in packages/paperclip-runner/src/protocol-actions — 50 commits (27 fixs), 73 files: “feat: let agents name prompt-only tasks (\#14761)”; “fix(runner): distinguish new skill authoring from source imports (\#18717)”; “Add core runner action contracts (\#12358)”; and 47 more (refs \#14761, \#18717, \#12358, \#18704, \#17114, …).
packages/paperclip-runner/src/protocol-actions · medium confidence · unverified
63 commits (49 fixes) fixing server/src/modules/run-dispatch
A fix in server/src/modules/run-dispatch — 63 commits (49 fixs), 12 files: “fix: verify ACP Stop and preserve safe continuation (\#13119)”; “fix: preserve conversation retries through execution cleanup (\#15463)”; “fix(dispatch): park a workspace-busy wait instead of recreating runs (\#19143)”; and 60 more (refs \#13119, \#15463, \#19143, \#20484, \#14967, …).
server/src/modules/run-dispatch · medium confidence · unverified
7 commits (4 fixes) fixing packages/db/src/\_\_fixtures\_\_
A fix in packages/db/src/\_\fixtures\\_ — 7 commits (4 fixs), 10 files: “Share the external Runner lifecycle and add strict Muse contracts (\#16444)”; “fix(db): release a postgres.js connection's receive buffer once it is fully read (\#21432)”; “fix(db): clean up owned PostgreSQL test servers (\#18627)”; and 4 more (refs \#16444, \#21432, \#18627, \#17831, \#13643, …).
packages/db/src/\\fixtures\\_ · medium confidence · unverified_
70 commits (49 fixes) fixing packages/paperclip-runner/src/drivers/opencode
A fix in packages/paperclip-runner/src/drivers/opencode — 70 commits (49 fixs), 32 files: “Bound native OpenCode assigned-tool catalog projection (\#17740)”; “refactor(runner): remove the direct assigned-gateway path (\#21311)”; “fix(opencode): export bounded tool argument diagnostics (\#18699)”; and 67 more (refs \#17740, \#21311, \#18699, \#12721, \#20964, …).
packages/paperclip-runner/src/drivers/opencode · medium confidence · unverified
83 commits (58 fixes) fixing server/src/modules/wake-queue
A fix in server/src/modules/wake-queue — 83 commits (58 fixs), 26 files: “fix(issues): finish a reassignment whose native stop settles after the request (\#19354)”; “fix(task-chat): keep messages sendable after a declined connection request (\#19331)”; “fix(queue): let board users discard agent-authored queued messages (\#21458)”; and 80 more (refs \#19354, \#19331, \#21458, \#20822, \#13139, …).
server/src/modules/wake-queue · medium confidence · unverified
Enhanced isolation, reliability, and fidelity across chat adapters and agent runtimes
This update introduces several targeted fixes and capability improvements across the platform's integration layers. In the Discord adapter, new configuration options allow for granular control over thread creation and gateway event monitoring, while the Teams adapter now provides detailed permission error reporting and simplified thread ID encoding. The Slack adapter improves file upload reliability by confirming message identity and handles file edits more accurately, and the Telegram adapter adds durable draft control for streaming and configurable download limits. On the agent runtime side, the Claude ACP patch enforces strict context isolation in sandboxed environments and exposes granular token usage metadata, while the Codex ACP patch upgrades the underlying SDK and applies similar isolation policies. Finally, the Discord.js WebSocket library is patched to prevent race conditions during connection teardown, and the ACPX runtime now supports environment variable inheritance for spawned agents. Also in this area: 1 commit (0 fixes) modifying docker, patches, rules; 1 commit (1 fix) fixing patches.
patches · medium confidence · unverified
Introduce built-in Hermes adapters with improved UI parsing
This change adds the \hermes\_local\ and \hermes\_gateway\ adapters as built-in components within the \packages/adapters/hermes\ package. The new UI parsers (\ui-parser.cjs\ and \gateway-ui-parser.cjs\) now strip ANSI escape codes from terminal output to ensure clean rendering in the Paperclip interface. Additionally, the gateway parser has been updated to correctly surface real reasoning text from \reasoning.available\ events, allowing users to see the agent's thought process rather than generic placeholders.
packages/adapters/hermes · high confidence
Test coverage
1 commit adding/updating tests in packages/db/src/\_\tests\\_; 5 commits adding/updating tests in packages/paperclip-runner/test/support; 840 commits adding/updating tests in tests; 85 commits adding/updating tests in packages/paperclip-runner/test/fixtures; Add prompt context test fixture for adapter-boundary tests; Added test helpers for embedded Postgres and ZIP archive creation; Expanded CLI test coverage for parity, configuration, and lifecycle commands; Initial test suite for the LLM Wiki plugin.
Dependencies
Introduce Paperclip CLI and standardize adapter packages on Node 24
This change introduces the new \paperclipai\ CLI package (\cli/package.json\) to orchestrate AI agent teams, bundling local adapters for Claude, Codex, Cursor, Gemini, Grok, Kimi, OpenCode, and Pi, along with the Hermes gateway adapter. It also standardizes the entire adapter suite (\packages/adapters/\*\) and core infrastructure packages (\packages/db\, \packages/mcp-server\, etc.) to require Node.js \>=24.11.0, upgrading \@types/node\ to v24 and TypeScript to v7.0.2, while aligning key dependencies such as \drizzle-orm\ (0.45.2), \commander\ (15.0.0), and \embedded-postgres\ (18.1.0-beta.16).
(dependencies) · high confidence
Upgrade lucide-react to v1.32.0
The lucide-react icon library has been upgraded from version 0.577.0 to 1.32.0. This update brings the latest icon set and component improvements to the application's UI.
ui · high confidence
Housekeeping
Release changelog documentation for v0.2.7 through v2026.416.0
The \releases/\ directory now contains structured markdown changelogs for versions v0.2.7, v0.3.0, v0.3.1, v2026.318.0, v2026.325.0, v2026.403.0, v2026.414.0, v2026.415.0, and v2026.416.0. These documents provide users with a consolidated view of new features (such as multi-user invites, execution policies, and plugin systems), behavioral improvements, and fixes included in each release, along with any necessary database migration steps.
releases · high confidence
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
How this codebase got here
Score
- CAI 51 → 55 (+3.9)
- Rubric changed (rubric-2026.10.5 → rubric-2026.11.4) — scores are not directly comparable.
Lenses
- Code Health 57 → 58 (+1.1)
- Architecture 48 → 56 (+8.0)
- Maturity 81 → 87 (+6.8)
- Readiness 49 → 55 (+6.9)
- Security 55 → 55 (+0.2)
- Domain Modelling 100 → 100 (+0.0)
- Event Sourcing 100 → 100 (+0.0)
- Accessibility 53 → 52 (-1.5)
- Performance 69 → 69 (+0.0)
Resolved (1041)
- AcpxCommandExecutor::poll_provider (cognitive 57) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_backend.rs)
- AcpxCommandExecutor::poll_provider (cyclomatic 25) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_backend.rs)
- AcpxProviderSession::poll_event (cognitive 68) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_session.rs)
- AcpxProviderSession::poll_event (cyclomatic 30) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_session.rs)
- AcpxProviderSession::start_turn (cognitive 23) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_session.rs)
- AcpxProviderSession::start_turn (cyclomatic 19) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_session.rs)
- AcpxSidecarTransport::request_inner (cognitive 16) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_sidecar_transport.rs)
- AgentDetail.AgentOverview (cognitive 26) (ui/src/pages/AgentDetail.tsx)
- AgentDetail.AgentOverview (cyclomatic 22) (ui/src/pages/AgentDetail.tsx)
- AgentDetail.LogViewer (cognitive 24) (ui/src/pages/AgentDetail.tsx)
- AgentDetail.LogViewer (cyclomatic 136) (ui/src/pages/AgentDetail.tsx)
- AgentDetail.LogViewer::appendLogContent (cognitive 19) (ui/src/pages/AgentDetail.tsx)
- AgentDetail.RunInvocationCard (cyclomatic 20) (ui/src/pages/AgentDetail.tsx)
- AgentDetail.WorkspaceOperationLogViewer (cyclomatic 16) (ui/src/pages/AgentDetail.tsx)
- AgentDetail.WorkspaceOperationsSection (cyclomatic 22) (ui/src/pages/AgentDetail.tsx)
- AgentDetail.production.LogViewer (cognitive 24) (ui/src/pages/AgentDetail.production.tsx)
- AgentDetail.production.LogViewer (cyclomatic 136) (ui/src/pages/AgentDetail.production.tsx)
- AgentDetail.production.LogViewer::appendLogContent (cognitive 19) (ui/src/pages/AgentDetail.production.tsx)
- AgentDetail.production.RunInvocationCard (cyclomatic 20) (ui/src/pages/AgentDetail.production.tsx)
- AgentDetail.production.WorkspaceOperationLogViewer (cyclomatic 16) (ui/src/pages/AgentDetail.production.tsx)
- …and 1021 more
New (3279)
- AcpxCommandExecutor::attach_run (cyclomatic 29) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_backend.rs)
- AcpxCommandExecutor::poll_provider_events (cognitive 65) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_backend.rs)
- AcpxCommandExecutor::poll_provider_events (cyclomatic 26) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_backend.rs)
- AcpxCommandExecutor::start_turn_in_open_session (cognitive 32) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_backend.rs)
- AcpxCommandExecutor::start_turn_in_open_session (cyclomatic 20) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_backend.rs)
- AcpxDurableState::validate_restored (cognitive 16) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_backend.rs)
- AcpxProviderDescriptor::validate_session (cognitive 16) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_backend.rs)
- AcpxProviderDescriptor::validate_session (cyclomatic 17) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_backend.rs)
- AcpxProviderSession::poll_output (cognitive 88) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_session.rs)
- AcpxProviderSession::poll_output (cyclomatic 47) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_session.rs)
- AcpxProviderSession::start_turn_timed (cognitive 29) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_session.rs)
- AcpxProviderSession::start_turn_timed (cyclomatic 25) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_session.rs)
- AcpxSidecarTransport::receive_response (cognitive 21) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_sidecar_transport.rs)
- AcpxSidecarTransport::start_for_agent (cyclomatic 18) (packages/paperclip-runner/runner/crates/runner-core/src/acpx_sidecar_transport.rs)
- AgentAdvancedTab.ConfigurationEditor (cognitive 39) (ui/src/pages/AgentAdvancedTab.tsx)
- AgentAdvancedTab.ConfigurationEditor (cyclomatic 40) (ui/src/pages/AgentAdvancedTab.tsx)
- AgentConfigSaveBar.AgentConfigSaveBar (cognitive 19) (ui/src/pages/agent-detail/AgentConfigSaveBar.tsx)
- AgentConfigSaveBar.AgentConfigSaveBar (cyclomatic 24) (ui/src/pages/agent-detail/AgentConfigSaveBar.tsx)
- AgentCostsPanel.AgentCostsPanel (cognitive 33) (ui/src/pages/AgentCostsPanel.tsx)
- AgentCostsPanel.AgentCostsPanel (cyclomatic 19) (ui/src/pages/AgentCostsPanel.tsx)
- …and 3259 more
Changes since last survey
- 300 commits — 118 feature/other, 182 fixes
By area
- server/src — 180 commits
- packages/paperclip-runner — 36 commits
- tests/runner-e2e — 22 commits
- ui/src — 20 commits
- packages/db — 7 commits
- .github/workflows — 5 commits
- tests/restart-chaos — 5 commits
- .github/scripts — 3 commits
- doc/plans — 3 commits
- packages/adapters — 3 commits
- packages/adapter-utils — 2 commits
- server/scripts — 2 commits
- tests/e2e — 2 commits
- (root) — 1 commit
- doc/runner-image-contract.md — 1 commit
- packages/kv-demo-mcp-server — 1 commit
- packages/plugins — 1 commit
- packages/shared — 1 commit
- scripts/tests — 1 commit
- scripts/ci — 1 commit
Notable commits
- fix: fix(accounting): recover closed legacy runs without inventing usage (#21493)
- fix: fix(acpx): admit a Claude tool call only for a tool use its turn announced (#21278)
- fix: fix(browser-tracing): end hidden loads, cap timeouts, backfill hard-load API spans, record list view (#21392)
- fix: fix(browser-tracing): send API spans only for measured page loads, without timing events (#21441)
- fix: fix(chat): do not post a completion report that an earlier reply already gave (#21401)
- fix: fix(ci): count a step cancelled as "A task was canceled." as runner loss when the log shows the shutdown (#21514)
- fix: fix(ci): keep the typecheck job working on stacked PRs and stop its CLI guidance test timing out (#21451)
- fix: fix(ci): re-run cancelled runs that lost a runner, and let runner-loss evidence win (#21291)
- fix: fix(claude-local): fail Opus 5.5 ACP runs early when the bundled Claude Code is too old (#13927)
- fix: fix(codex): preserve sandbox certificate trust in Codex shell commands (#20364)
- fix: fix(connections): answer setup questions with a setup link in ranked results too (#21428)
- fix: fix(connections): keep machine sign-in secrets and settings in one locked commit (#21566)
- fix: fix(connections): show the setup card unless the person asked to set up the connection (#21400)
- fix: fix(connectors): keep result classification alive during run progress (#20763)
- fix: fix(daytona): bound the duplex channel close so a stalled kill cannot retire the worker (#21471)
- fix: fix(db): release a postgres.js connection's receive buffer once it is fully read (#21432)
- fix: fix(diagnostics): report Daytona acquisition state for runs retried as provider outages (#21476)
- fix: fix(discord): refresh due command registration after task drains (#21573)
- fix: fix(dispatch): bound how long a queued run waits and keep a person's interrupted Retry person-first (#21349)
- fix: fix(dispatch): start the assigned-work sweep's continuations and count only system recovery for the recovery share (#21391)
- …and 280 more
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
Survey your own repository
paperclipai/paperclip was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.
About this page
- The score is its most recent published measurement, taken on 14 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
- Measured at commit 7c0c3c4f31a135cf58d07ebaa2e75451bf14c194 — the exact code this score is about.
- Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
- Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.65+preprod-e1a3b69fc8ee.