pi-mono/packages/coding-agent
Petr Houška cc44fa2169
fix(coding-agent): weigh tool names above descriptions in tool search (#11625)
Follow-up to #11440 for the latest comment on #11331.

Problem: the ranker scored a tool as one bag of words. A query term in
the tool's name counted like a mention in its description, and the
server's instructions were copied into every tool's text, which
lengthened it and lowered its score. Models often add words to a tool
name, so `peekaboo app` ranked `mcp__peekaboo__app` 14th: other peekaboo
tools mention "app" in shorter descriptions, and its own description
says "applications".

Fix: `Bm25Ranker` scores three fields separately:
- name: a query term in the name counts 3x its IDF; the description part
of BM25 is at most 2.2x, so a name match beats any number of description
mentions;
- description and schema text: BM25 as before, length-normalized on this
field only;
- namespace name, description, and instructions: 0.5x IDF per matching
term, without length normalization.

A tool whose whole local name (last `__` segment) is in the query gets a
bonus worth one more match of every query term, so it mostly wins
(`peekaboo app`, `describe app`, `read thread_read state`). A query that
is exactly a tool's name still ranks it first (#11440). Applies to
`tool_search` and codemode `searchTools()`.

Not included: the comment's second point (loading a deferred tool on a
direct call instead of `Tool X not found`). That error comes from
`prepareToolCall` in `packages/agent`, which has no hook for unknown
tools; it needs an agent-loop API change.
2026-10-30 21:56:03 +01:00
..
docs docs(coding-agent): document which working directory resumed sessions use (#11617) 2026-10-30 17:22:05 +00:00
examples fix(tui,coding-agent): handle selection page keys in all scrolling lists 2026-10-28 19:05:21 +01:00
install-lock fix(coding-agent): update undici to 8.12.3 for security advisories 2026-10-26 13:50:55 +01:00
schemas feat(coding-agent): extensions changelog (#8790) 2026-10-28 11:25:04 +01:00
scripts docs(ai,coding-agent): generate models.json reference from schemas (#11038) 2026-10-16 21:53:00 +01:00
src fix(coding-agent): weigh tool names above descriptions in tool search (#11625) 2026-10-30 21:56:03 +01:00
test fix(coding-agent): weigh tool names above descriptions in tool search (#11625) 2026-10-30 21:56:03 +01:00
.gitignore Fix tool call ID normalization for cross-provider switches to Anthropic/GitHub Copilot 2026-01-13 04:07:10 +01:00
CHANGELOG.md fix(coding-agent): weigh tool names above descriptions in tool search (#11625) 2026-10-30 21:56:03 +01:00
package.json fix(coding-agent): update undici to 8.12.3 for security advisories 2026-10-26 13:50:55 +01:00
README.md feat(coding-agent): add Nix flake (#9137) 2026-10-02 18:30:51 +02:00
tsconfig.build.json feat(coding-agent): remove the experimental server stack and the client, protocol, and server packages 2026-10-12 10:41:59 +00:00
tsconfig.examples.json chore: migrate pi packages to earendil works scope 2026-05-07 15:59:42 +02:00
vitest.config.ts fix: use bounded runtime paths for Unix sockets 2026-08-14 17:02:03 +03:00

Pi logo

Discord npm

New issues and PRs from new contributors are closed automatically. Maintainers review closed submissions daily. See CONTRIBUTING.md.

Pi

Pi is a minimal, extensible agent harness that you can make your own.

Adapt Pi to your workflows, not the other way around. Customize Pi with extensions, skills, prompt templates, and themes. Bundle them as Pi packages and share via npm or git.

Pi ships with powerful defaults but skips features like sub-agents and plan mode. Ask Pi to build what you want, or install a package that does it your way.

Use Pi interactively, automate it in print or JSON mode, control it over RPC, or build apps with the Pi TypeScript SDK. See OpenClaw for a real-world integration.

Getting started

Install the command-line interface:

curl -fsSL https://pi.dev/install.sh | sh

On Windows:

powershell -c "irm https://pi.dev/install.ps1 | iex"

The installer pins all dependencies and updates Pi with pi update. Alternatively, install directly with npm, which does not pin transitive dependencies:

npm install -g --ignore-scripts @earendil-works/pi-coding-agent

Pi requires Node.js 22.19 or newer. The macOS, Linux, and Windows installers can install it if needed. Pi does not require dependency lifecycle scripts for a normal npm installation.

On macOS and Linux, Nix users can install the latest release with nix profile add github:earendil-works/pi/stable. See the quickstart for updating and pinning releases.

Start Pi in the directory where you want it to work:

cd /path/to/project
pi

For a built-in AI provider, run /login inside Pi to connect a subscription or API key. Then give Pi a task.

See the documentation for full setup and usage instructions.

Share your OSS coding agent sessions

If you use Pi for open source work, please share your coding agent sessions.

Public OSS session data helps improve models, prompts, tools, and evaluations using real development workflows.

For the full explanation, see this post on X.

To publish sessions, use badlogic/pi-share-hf using a Hugging Face account and the Hugging Face CLI.

Development

Clone the repository, install its dependencies, and run Pi from source:

git clone https://github.com/earendil-works/pi
cd pi
npm install --ignore-scripts
./pi-test.sh

pi-test.sh can be called from any directory and preserves the caller's working directory.

Before submitting changes, run:

npm run check
./test.sh

Read CONTRIBUTING.md before opening an issue or pull request. It defines the contribution gate, issue quality bar, and required checks. Read AGENTS.md for repository-specific implementation, testing, dependency, and release rules.

License

MIT