getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-15 08:03:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
Composable agent runtime monorepo built on the pi ecosystem
2995 commits 13 branches 2 tags 46 MiB
Find a file
jeremiahgaylord-web cf656c169c
fix(ai): don't cache false for Vertex ADC credentials during async import race (#1550) 
`hasVertexAdcCredentials()` uses dynamic imports to load `node:fs`,
`node:os`, and `node:path` to avoid breaking browser/Vite builds. These
imports are fired eagerly but resolve asynchronously. If the function is
called during gateway startup before those promises resolve, `_existsSync`,
`_homedir`, and `_join` are still null — causing the function to cache
`false` permanently and never re-evaluate.

This means users with valid `GOOGLE_APPLICATION_CREDENTIALS`,
`GOOGLE_CLOUD_PROJECT`, and `GOOGLE_CLOUD_LOCATION` configured are silently
treated as unauthenticated for Vertex AI. Calls fall back to the AI Studio
endpoint (generativelanguage.googleapis.com) which has much stricter rate
limits, causing unexpected 429 errors even though Vertex credentials are
correctly configured.

Fix: in Node.js/Bun environments, return false without caching when the
async modules aren't loaded yet, so the next call retries. Only cache false
permanently in browser environments where `fs` is genuinely unavailable.

Co-authored-by: Jeremiah Gaylord <jeremiahgaylord-web@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-26 00:31:16 +01:00
.github chore: approve contributor barapa 2026-02-12 19:52:51 +00:00
.husky Add husky pre-commit hook for formatting and type checking 2025-08-11 21:15:37 +02:00
.pi docs: skip generated model catalog changes in changelog audit prompt 2026-02-25 23:42:57 +01:00
packages fix(ai): don't cache false for Vertex ADC credentials during async import race (#1550) 2026-02-26 00:31:16 +01:00
scripts fix(tui): externalize koffi from bun binary builds 2026-02-22 14:29:21 +01:00
.gitignore fix(coding-agent): normalize raw git URLs in extension source matching 2026-01-22 14:19:04 +01:00
AGENTS.md docs: fix test command path for vitest via tsx 2026-02-06 11:38:11 +01:00
biome.json WIP: Remove global state from pi-ai OAuth/API key handling 2025-12-25 01:01:03 +01:00
CONTRIBUTING.md Fix Discord link 2026-02-01 22:25:07 +01:00
LICENSE Initial monorepo setup with npm workspaces and dual TypeScript configuration 2025-08-09 17:18:38 +02:00
package-lock.json fix(coding-agent): harden fd/rg bootstrap on windows 2026-02-26 00:19:43 +01:00
package.json fix(tui): enable VT input mode on Windows (#1495) 2026-02-14 01:45:11 +01:00
pi-mono.code-workspace Update README to include github-copilot, google-gemini-cli, google-antigravity providers 2025-12-21 20:17:12 +01:00
pi-test.sh fix: handle empty args array in pi-test.sh 2026-01-25 23:47:35 +01:00
README.md Extend OSS vacation to March 2, 2026 2026-02-22 19:56:08 +01:00
test.sh fix(coding-agent): tighten session_before emit typing and test env filtering 2026-02-06 11:59:25 +01:00
tsconfig.base.json Try fixing root level compiles 2025-12-03 14:16:00 +01:00
tsconfig.json Remove proxy package 2025-12-30 22:42:21 +01:00

README.md

🏖️ OSS Vacation

Issue tracker and PRs reopen March 2, 2026.

All PRs will be auto-closed until then. Approved contributors can submit PRs after vacation without reapproval. For support, join Discord.

pi logo

Discord Build status

pi.dev domain graciously donated by

Exy mascot
exe.dev

Pi Monorepo

Looking for the pi coding agent? See packages/coding-agent for installation and usage.

Tools for building AI agents and managing LLM deployments.

Packages

Package Description
@mariozechner/pi-ai Unified multi-provider LLM API (OpenAI, Anthropic, Google, etc.)
@mariozechner/pi-agent-core Agent runtime with tool calling and state management
@mariozechner/pi-coding-agent Interactive coding agent CLI
@mariozechner/pi-mom Slack bot that delegates messages to the pi coding agent
@mariozechner/pi-tui Terminal UI library with differential rendering
@mariozechner/pi-web-ui Web components for AI chat interfaces
@mariozechner/pi-pods CLI for managing vLLM deployments on GPU pods

Contributing

See CONTRIBUTING.md for contribution guidelines and AGENTS.md for project-specific rules (for both humans and agents).

Development

npm install          # Install all dependencies
npm run build        # Build all packages
npm run check        # Lint, format, and type check
./test.sh            # Run tests (skips LLM-dependent tests without API keys)
./pi-test.sh         # Run pi from sources (must be run from repo root)

Note: npm run check requires npm run build to be run first. The web-ui package uses tsc which needs compiled .d.ts files from dependencies.

License

MIT