@xberg-io/opencode-xberg 1.3.8 → 1.4.0

package/README.md

@@ -17,6 +17,20 @@ Self-host:
 /plugin install xberg@xberg
 ```
 
+### Kimi installation and compatibility
+
+From a checkout of this repository, install with the Python Kimi CLI version used for native
+plugin validation:
+
+```sh
+uvx --from kimi-cli==1.51.0 kimi plugin install ./plugin
+```
+
+Native plugin installation was validated with Python Kimi CLI 1.51.0. The replacement
+`@moonshot-ai/kimi-code` 2.1.1 does not provide a `plugin` CLI subcommand; its interactive
+plugin loading has not been verified. These results do not establish compatibility with
+newer Kimi releases.
+
 ### Pi
 
 From a checkout of this repository, run:
@@ -76,12 +90,12 @@ sudo apt install tesseract-ocr-*   # Debian/Ubuntu
 | Skill | Trigger |
 |-------|---------|
 | **xberg** | Extract text, tables, metadata, and images from 107 document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg. Use when writing code that calls Xberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format), batch processing, error handling, and plugins. |
-| **extracting-with-ocr** | Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning. |
-| **extracting-tables** | Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits. |
-| **chunking** | Use when splitting extracted text into chunks for LLM context windows or RAG ingestion. Covers chunk size, overlap, markdown/yaml/semantic chunkers, tokenizer-based sizing, and the standalone `chunk` command. |
-| **extracting-keywords** | Use when extracting keywords (YAKE/RAKE), detecting document language, or generating embeddings for RAG and search. Covers the keyword config, `--detect-language`, and the standalone `embed` command. |
-| **batch-extraction** | Use when extracting from many files at once with shared config, bounded parallelism, per-file overrides, and error recovery. Covers the `batch` command, `--file-configs`, `--max-concurrent`, and output layout. |
-| **picking-a-format** | Use when choosing an output format for extracted documents — text, markdown, djot, html, or JSON. Maps consumer (LLM, parser, archive) to the right `--format` / `--content-format` pair. |
+| **xberg-extracting-with-ocr** | Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning. |
+| **xberg-extracting-tables** | Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits. |
+| **xberg-chunking** | Use when splitting extracted text into chunks for LLM context windows or RAG ingestion. Covers chunk size, overlap, markdown/yaml/semantic chunkers, tokenizer-based sizing, and the standalone `chunk` command. |
+| **xberg-extracting-keywords** | Use when extracting keywords (YAKE/RAKE), detecting document language, or generating embeddings for RAG and search. Covers the keyword config, `--detect-language`, and the standalone `embed` command. |
+| **xberg-batch-extraction** | Use when extracting from many files at once with shared config, bounded parallelism, per-file overrides, and error recovery. Covers the `batch` command, `--file-configs`, `--max-concurrent`, and output layout. |
+| **xberg-picking-a-format** | Use when choosing an output format for extracted documents — text, markdown, djot, html, or JSON. Maps consumer (LLM, parser, archive) to the right `--format` / `--content-format` pair. |
 
 **Reference materials** (linked from the `xberg` skill):
 
@@ -148,9 +162,9 @@ Edit `plugin/.ai-rulez` sources, then run these commands from the repository roo
 with a Pi-capable ai-rulez v5 binary installed:
 
 ```bash
-task plugin:generate
-task plugin:verify
-task plugin:test
+mise run plugin:generate
+mise run plugin:verify
+mise run plugin:test
 ```
 
 CI builds the generator from a pinned source revision and verifies the generated
@@ -167,3 +181,55 @@ MIT. The skill content uses Elastic-2.0 references to the upstream [xberg](https
 - **Marketplace**: this repo — `/plugin marketplace add xberg-io/xberg`
 - **Upstream**: [xberg-io/xberg](https://github.com/xberg-io/xberg)
 - **Related plugins**: [crawlberg](https://github.com/xberg-io/crawlberg)
+
+## Generated runtime bundles
+
+`plugin/.ai-rulez/config.toml` loads `config.plugins.toml` through the `plugins` layer;
+skills, commands and runtime adapters are authored alongside it. AI-Rulez (latest, minimum 5.7.0)
+generates all eleven supported runtimes: Claude, Cursor, Codex, Gemini, Kimi, OpenCode, Factory,
+Hermes, Pi, Agent Plugins and Copilot. Codex ships both manifest layouts; repository-root
+Claude and Codex marketplace indexes point to the `plugin` bundle. Cursor also has a marketplace index.
+
+Pi packages skills and prompts without MCP integration. Copilot packages skills and MCP configuration, but does not package slash commands or hooks.
+Hermes includes a Python package under `.hermes/package`; OpenCode and Pi share the npm package.
+The Agent Plugins manifest uses the stable 1.0 specification. Runtime capabilities differ;
+install the CLI before using skills in a runtime without MCP registration.
+
+Run `ai-rulez generate --plugin` from the repository root to regenerate and
+`ai-rulez verify --plugin` to compare current source output and provenance.
+The release workflow packages every runtime into a deterministic archive, checksums,
+and marketplace metadata; npm and PyPI retain their existing publishing jobs.
+
+## Hermes runtime setup
+
+Install the product CLI with MCP support and put it on Hermes' PATH before using the plugin.
+The Hermes adapter registers every bundled skill under the product namespace and provides
+`xberg_call`, which calls the selected native MCP tool with `tool_arguments` through a local
+stdio session. Select `tool: "list_tools"` first to inspect the server's exact request schemas. Hermes skills are selected explicitly; they are not automatically appended to the
+system prompt. Enable the plugin in Hermes configuration; project plugins also require
+`HERMES_ENABLE_PROJECT_PLUGINS=true`.
+
+The bridge uses the installed CLI directly. The auto-installing launchers used by other MCP clients
+are not included in the Hermes Python wheel. Provider credentials are inherited from the environment,
+and are needed for provider-backed requests. Missing CLIs, unavailable tools and model preparation
+fail with an actionable request error. CLI result data remains untrusted document content.
+
+## Public Agent Skills
+
+The repository-root `skills/` directory contains the same generated skills and supporting
+resources as `plugin/skills/`. Install them independently of a plugin runtime:
+
+```sh
+npx skills add xberg-io/xberg --skill xberg
+```
+
+Edit `plugin/.ai-rulez/skills`, then run `mise run plugin:generate` to regenerate runtime
+bundles and synchronize the public export. `mise run plugin:verify` checks both projections;
+`mise run plugin:skills:test` verifies resource freshness, ownership and symlink protection.
+The public ownership manifest records SHA-256 hashes of every exported file.
+
+Download integrity: the launcher currently relies on HTTPS for direct binary downloads.
+Verify release checksums separately when available before manually installing an archive.
+
+Launcher and visual assets are authored in `plugin/.ai-rulez/scripts/` and
+`plugin/.ai-rulez/assets/`; `mise run plugin:generate` copies them into the runtime bundle.

package/assets/icon.svg

@@ -1,11 +1,18 @@
-<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 256" width="256" height="256">
-  <rect width="256" height="256" rx="48" fill="#1F6FEB" />
-  <path
-    d="M64 64 L152 64 L192 104 L192 200 C192 204.4 188.4 208 184 208 L64 208 C59.6 208 56 204.4 56 200 L56 72 C56 67.6 59.6 64 64 64 Z"
-    fill="white"
+<svg
+  xmlns="http://www.w3.org/2000/svg"
+  viewBox="0 0 309 309"
+  width="309"
+  height="309"
+  role="img"
+  aria-label="Xberg Rotated Junction V5 dark background"
+>
+  <title>Xberg Rotated Junction V5 dark background</title>
+
+  <image
+    href="data:image/png;base64,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"
+    x="0"
+    y="0"
+    width="309"
+    height="309"
   />
-  <path d="M152 64 L152 96 C152 100.4 155.6 104 160 104 L192 104 Z" fill="#1F6FEB" />
-  <rect x="80" y="128" width="88" height="12" rx="6" fill="#1F6FEB" />
-  <rect x="80" y="152" width="96" height="12" rx="6" fill="#1F6FEB" />
-  <rect x="80" y="176" width="64" height="12" rx="6" fill="#1F6FEB" />
 </svg>

package/package.json

@@ -1,6 +1,11 @@
 {
+  "author": {
+    "email": "contact@xberg.io",
+    "name": "Kreuzberg, Inc.",
+    "url": "https://xberg.io"
+  },
   "dependencies": {
-    "@opencode/plugin": "^2.0.20"
+    "@opencode/plugin": "^2.2.3"
   },
   "description": "Local document extraction: text, tables, metadata, images from 107 formats with optional OCR.",
   "exports": {
@@ -12,13 +17,68 @@
     ".opencode/commands/xberg-extract.md",
     ".opencode/commands/xberg-ocr.md",
     ".opencode/plugins/xberg.js",
-    ".opencode/skills/batch-extraction/SKILL.md",
-    ".opencode/skills/chunking/SKILL.md",
-    ".opencode/skills/extracting-keywords/SKILL.md",
-    ".opencode/skills/extracting-tables/SKILL.md",
-    ".opencode/skills/extracting-with-ocr/SKILL.md",
-    ".opencode/skills/picking-a-format/SKILL.md",
+    ".opencode/skills/xberg-batch-extraction/SKILL.md",
+    ".opencode/skills/xberg-batch-extraction/index.md",
+    ".opencode/skills/xberg-batch-extraction/references/advanced-features.md",
+    ".opencode/skills/xberg-batch-extraction/references/cli-reference.md",
+    ".opencode/skills/xberg-batch-extraction/references/configuration.md",
+    ".opencode/skills/xberg-batch-extraction/references/nodejs-api.md",
+    ".opencode/skills/xberg-batch-extraction/references/other-bindings.md",
+    ".opencode/skills/xberg-batch-extraction/references/python-api.md",
+    ".opencode/skills/xberg-batch-extraction/references/rust-api.md",
+    ".opencode/skills/xberg-batch-extraction/references/supported-formats.md",
+    ".opencode/skills/xberg-chunking/SKILL.md",
+    ".opencode/skills/xberg-chunking/index.md",
+    ".opencode/skills/xberg-chunking/references/advanced-features.md",
+    ".opencode/skills/xberg-chunking/references/cli-reference.md",
+    ".opencode/skills/xberg-chunking/references/configuration.md",
+    ".opencode/skills/xberg-chunking/references/nodejs-api.md",
+    ".opencode/skills/xberg-chunking/references/other-bindings.md",
+    ".opencode/skills/xberg-chunking/references/python-api.md",
+    ".opencode/skills/xberg-chunking/references/rust-api.md",
+    ".opencode/skills/xberg-chunking/references/supported-formats.md",
+    ".opencode/skills/xberg-extracting-keywords/SKILL.md",
+    ".opencode/skills/xberg-extracting-keywords/index.md",
+    ".opencode/skills/xberg-extracting-keywords/references/advanced-features.md",
+    ".opencode/skills/xberg-extracting-keywords/references/cli-reference.md",
+    ".opencode/skills/xberg-extracting-keywords/references/configuration.md",
+    ".opencode/skills/xberg-extracting-keywords/references/nodejs-api.md",
+    ".opencode/skills/xberg-extracting-keywords/references/other-bindings.md",
+    ".opencode/skills/xberg-extracting-keywords/references/python-api.md",
+    ".opencode/skills/xberg-extracting-keywords/references/rust-api.md",
+    ".opencode/skills/xberg-extracting-keywords/references/supported-formats.md",
+    ".opencode/skills/xberg-extracting-tables/SKILL.md",
+    ".opencode/skills/xberg-extracting-tables/index.md",
+    ".opencode/skills/xberg-extracting-tables/references/advanced-features.md",
+    ".opencode/skills/xberg-extracting-tables/references/cli-reference.md",
+    ".opencode/skills/xberg-extracting-tables/references/configuration.md",
+    ".opencode/skills/xberg-extracting-tables/references/nodejs-api.md",
+    ".opencode/skills/xberg-extracting-tables/references/other-bindings.md",
+    ".opencode/skills/xberg-extracting-tables/references/python-api.md",
+    ".opencode/skills/xberg-extracting-tables/references/rust-api.md",
+    ".opencode/skills/xberg-extracting-tables/references/supported-formats.md",
+    ".opencode/skills/xberg-extracting-with-ocr/SKILL.md",
+    ".opencode/skills/xberg-extracting-with-ocr/index.md",
+    ".opencode/skills/xberg-extracting-with-ocr/references/advanced-features.md",
+    ".opencode/skills/xberg-extracting-with-ocr/references/cli-reference.md",
+    ".opencode/skills/xberg-extracting-with-ocr/references/configuration.md",
+    ".opencode/skills/xberg-extracting-with-ocr/references/nodejs-api.md",
+    ".opencode/skills/xberg-extracting-with-ocr/references/other-bindings.md",
+    ".opencode/skills/xberg-extracting-with-ocr/references/python-api.md",
+    ".opencode/skills/xberg-extracting-with-ocr/references/rust-api.md",
+    ".opencode/skills/xberg-extracting-with-ocr/references/supported-formats.md",
+    ".opencode/skills/xberg-picking-a-format/SKILL.md",
+    ".opencode/skills/xberg-picking-a-format/index.md",
+    ".opencode/skills/xberg-picking-a-format/references/advanced-features.md",
+    ".opencode/skills/xberg-picking-a-format/references/cli-reference.md",
+    ".opencode/skills/xberg-picking-a-format/references/configuration.md",
+    ".opencode/skills/xberg-picking-a-format/references/nodejs-api.md",
+    ".opencode/skills/xberg-picking-a-format/references/other-bindings.md",
+    ".opencode/skills/xberg-picking-a-format/references/python-api.md",
+    ".opencode/skills/xberg-picking-a-format/references/rust-api.md",
+    ".opencode/skills/xberg-picking-a-format/references/supported-formats.md",
     ".opencode/skills/xberg/SKILL.md",
+    ".opencode/skills/xberg/index.md",
     ".opencode/skills/xberg/references/advanced-features.md",
     ".opencode/skills/xberg/references/cli-reference.md",
     ".opencode/skills/xberg/references/configuration.md",
@@ -29,13 +89,68 @@
     ".opencode/skills/xberg/references/supported-formats.md",
     ".pi/prompts/xberg-extract.md",
     ".pi/prompts/xberg-ocr.md",
-    ".pi/skills/batch-extraction/SKILL.md",
-    ".pi/skills/chunking/SKILL.md",
-    ".pi/skills/extracting-keywords/SKILL.md",
-    ".pi/skills/extracting-tables/SKILL.md",
-    ".pi/skills/extracting-with-ocr/SKILL.md",
-    ".pi/skills/picking-a-format/SKILL.md",
+    ".pi/skills/xberg-batch-extraction/SKILL.md",
+    ".pi/skills/xberg-batch-extraction/index.md",
+    ".pi/skills/xberg-batch-extraction/references/advanced-features.md",
+    ".pi/skills/xberg-batch-extraction/references/cli-reference.md",
+    ".pi/skills/xberg-batch-extraction/references/configuration.md",
+    ".pi/skills/xberg-batch-extraction/references/nodejs-api.md",
+    ".pi/skills/xberg-batch-extraction/references/other-bindings.md",
+    ".pi/skills/xberg-batch-extraction/references/python-api.md",
+    ".pi/skills/xberg-batch-extraction/references/rust-api.md",
+    ".pi/skills/xberg-batch-extraction/references/supported-formats.md",
+    ".pi/skills/xberg-chunking/SKILL.md",
+    ".pi/skills/xberg-chunking/index.md",
+    ".pi/skills/xberg-chunking/references/advanced-features.md",
+    ".pi/skills/xberg-chunking/references/cli-reference.md",
+    ".pi/skills/xberg-chunking/references/configuration.md",
+    ".pi/skills/xberg-chunking/references/nodejs-api.md",
+    ".pi/skills/xberg-chunking/references/other-bindings.md",
+    ".pi/skills/xberg-chunking/references/python-api.md",
+    ".pi/skills/xberg-chunking/references/rust-api.md",
+    ".pi/skills/xberg-chunking/references/supported-formats.md",
+    ".pi/skills/xberg-extracting-keywords/SKILL.md",
+    ".pi/skills/xberg-extracting-keywords/index.md",
+    ".pi/skills/xberg-extracting-keywords/references/advanced-features.md",
+    ".pi/skills/xberg-extracting-keywords/references/cli-reference.md",
+    ".pi/skills/xberg-extracting-keywords/references/configuration.md",
+    ".pi/skills/xberg-extracting-keywords/references/nodejs-api.md",
+    ".pi/skills/xberg-extracting-keywords/references/other-bindings.md",
+    ".pi/skills/xberg-extracting-keywords/references/python-api.md",
+    ".pi/skills/xberg-extracting-keywords/references/rust-api.md",
+    ".pi/skills/xberg-extracting-keywords/references/supported-formats.md",
+    ".pi/skills/xberg-extracting-tables/SKILL.md",
+    ".pi/skills/xberg-extracting-tables/index.md",
+    ".pi/skills/xberg-extracting-tables/references/advanced-features.md",
+    ".pi/skills/xberg-extracting-tables/references/cli-reference.md",
+    ".pi/skills/xberg-extracting-tables/references/configuration.md",
+    ".pi/skills/xberg-extracting-tables/references/nodejs-api.md",
+    ".pi/skills/xberg-extracting-tables/references/other-bindings.md",
+    ".pi/skills/xberg-extracting-tables/references/python-api.md",
+    ".pi/skills/xberg-extracting-tables/references/rust-api.md",
+    ".pi/skills/xberg-extracting-tables/references/supported-formats.md",
+    ".pi/skills/xberg-extracting-with-ocr/SKILL.md",
+    ".pi/skills/xberg-extracting-with-ocr/index.md",
+    ".pi/skills/xberg-extracting-with-ocr/references/advanced-features.md",
+    ".pi/skills/xberg-extracting-with-ocr/references/cli-reference.md",
+    ".pi/skills/xberg-extracting-with-ocr/references/configuration.md",
+    ".pi/skills/xberg-extracting-with-ocr/references/nodejs-api.md",
+    ".pi/skills/xberg-extracting-with-ocr/references/other-bindings.md",
+    ".pi/skills/xberg-extracting-with-ocr/references/python-api.md",
+    ".pi/skills/xberg-extracting-with-ocr/references/rust-api.md",
+    ".pi/skills/xberg-extracting-with-ocr/references/supported-formats.md",
+    ".pi/skills/xberg-picking-a-format/SKILL.md",
+    ".pi/skills/xberg-picking-a-format/index.md",
+    ".pi/skills/xberg-picking-a-format/references/advanced-features.md",
+    ".pi/skills/xberg-picking-a-format/references/cli-reference.md",
+    ".pi/skills/xberg-picking-a-format/references/configuration.md",
+    ".pi/skills/xberg-picking-a-format/references/nodejs-api.md",
+    ".pi/skills/xberg-picking-a-format/references/other-bindings.md",
+    ".pi/skills/xberg-picking-a-format/references/python-api.md",
+    ".pi/skills/xberg-picking-a-format/references/rust-api.md",
+    ".pi/skills/xberg-picking-a-format/references/supported-formats.md",
     ".pi/skills/xberg/SKILL.md",
+    ".pi/skills/xberg/index.md",
     ".pi/skills/xberg/references/advanced-features.md",
     ".pi/skills/xberg/references/cli-reference.md",
     ".pi/skills/xberg/references/configuration.md",
@@ -66,12 +181,12 @@
       "./.pi/prompts/xberg-ocr.md"
     ],
     "skills": [
-      "./.pi/skills/batch-extraction",
-      "./.pi/skills/chunking",
-      "./.pi/skills/extracting-keywords",
-      "./.pi/skills/extracting-tables",
-      "./.pi/skills/extracting-with-ocr",
-      "./.pi/skills/picking-a-format",
+      "./.pi/skills/xberg-batch-extraction",
+      "./.pi/skills/xberg-chunking",
+      "./.pi/skills/xberg-extracting-keywords",
+      "./.pi/skills/xberg-extracting-tables",
+      "./.pi/skills/xberg-extracting-with-ocr",
+      "./.pi/skills/xberg-picking-a-format",
       "./.pi/skills/xberg"
     ]
   },
@@ -80,5 +195,5 @@
     "url": "https://github.com/xberg-io/xberg"
   },
   "type": "module",
-  "version": "1.3.8"
-}
+  "version": "1.4.0"
+}

package/scripts/mcp-launch.sh

@@ -47,12 +47,13 @@ if have "$BINARY_NAME"; then
 fi
 
 if want npx && have npx; then
-  log "probing npx $NPM_PKG@latest ..."
+  log "resolving npx $NPM_PKG@latest ..."
   scratch="$(mktemp -d)"
-  if (cd "$scratch" && npx -y "$NPM_PKG@latest" --version >/dev/null 2>&1); then
-    log "launching via npx $NPM_PKG@latest"
-    cd "$scratch"
-    exec npx -y "$NPM_PKG@latest" "$@"
+  # Resolve in an empty project, then execute the selected binary in the caller's cwd. ~keep
+  if npm_bin="$(cd "$scratch" && npx -y --package "$NPM_PKG@latest" --call "command -v ${BINARY_NAME%.exe}" 2>/dev/null)" && runnable "$npm_bin"; then
+    rm -rf "$scratch"
+    log "launching npm package binary $npm_bin"
+    exec "$npm_bin" "$@"
   fi
   rm -rf "$scratch"
   log "npx $NPM_PKG not available (no CLI bin yet); falling through"