co-mono/AGENTS.md

Development Rules

First Message

If the user did not give you a concrete task in their first message, read README.md, then ask which module(s) to work on. Based on the answer, read the relevant README.md files in parallel.

• packages/ai/README.md
• packages/tui/README.md
• packages/agent/README.md
• packages/coding-agent/README.md
• packages/mom/README.md
• packages/pods/README.md
• packages/web-ui/README.md

Code Quality

• No any types unless absolutely necessary
• Check node_modules for external API type definitions instead of guessing
• NEVER use inline imports - no await import("./foo.js"), no import("pkg").Type in type positions, no dynamic imports for types. Always use standard top-level imports.
• NEVER remove or downgrade code to fix type errors from outdated dependencies; upgrade the dependency instead
• Always ask before removing functionality or code that appears to be intentional

Commands

• After code changes (not documentation changes): npm run check (get full output, no tail). Fix all errors, warnings, and infos before committing.
• NEVER run: npm run dev, npm run build, npm test
• Only run specific tests if user instructs: npm test -- test/specific.test.ts
• NEVER commit unless user asks

GitHub Issues

When reading issues:

• Always read all comments on the issue
• Use this command to get everything in one call:

  gh issue view <number> --json title,body,comments,labels,state
  

When creating issues:

• Add pkg:* labels to indicate which package(s) the issue affects
  • Available labels: pkg:agent, pkg:ai, pkg:coding-agent, pkg:mom, pkg:pods, pkg:tui, pkg:web-ui
• If an issue spans multiple packages, add all relevant labels

When closing issues via commit:

• Include fixes #<number> or closes #<number> in the commit message
• This automatically closes the issue when the commit is merged

PR Workflow

• Analyze PRs without pulling locally first
• If the user approves: create a feature branch, pull PR, rebase on main, apply adjustments, commit, merge into main, push, close PR, and leave a comment in the user's tone
• You never open PRs yourself. We work in feature branches until everything is according to the user's requirements, then merge into main, and push.

Tools

• GitHub CLI for issues/PRs
• Add package labels to issues/PRs: pkg:agent, pkg:ai, pkg:coding-agent, pkg:mom, pkg:pods, pkg:tui, pkg:web-ui

Style

• Keep answers short and concise
• No emojis in commits, issues, PR comments, or code
• No fluff or cheerful filler text
• Technical prose only, be kind but direct (e.g., "Thanks @user" not "Thanks so much @user!")

Changelog

Location: packages/*/CHANGELOG.md (each package has its own)

Format

Use these sections under ## [Unreleased]:

• ### Breaking Changes - API changes requiring migration
• ### Added - New features
• ### Changed - Changes to existing functionality
• ### Fixed - Bug fixes
• ### Removed - Removed features

Rules

• Before adding entries, read the full [Unreleased] section to see which subsections already exist
• New entries ALWAYS go under ## [Unreleased] section
• Append to existing subsections (e.g., ### Fixed), do not create duplicates
• NEVER modify already-released version sections (e.g., ## [0.12.2])
• Each version section is immutable once released

Attribution

• Internal changes (from issues): Fixed foo bar ([#123](https://github.com/badlogic/pi-mono/issues/123))
• External contributions: Added feature X ([#456](https://github.com/badlogic/pi-mono/pull/456) by [@username](https://github.com/username))

Adding a New LLM Provider (packages/ai)

Adding a new provider requires changes across multiple files:

1. Core Types (packages/ai/src/types.ts)

• Add API identifier to Api type union (e.g., "bedrock-converse-stream")
• Create options interface extending StreamOptions
• Add mapping to ApiOptionsMap
• Add provider name to KnownProvider type union

2. Provider Implementation (packages/ai/src/providers/)

Create provider file exporting:

• stream<Provider>() function returning AssistantMessageEventStream
• Message/tool conversion functions
• Response parsing emitting standardized events (text, tool_call, thinking, usage, stop)

3. Stream Integration (packages/ai/src/stream.ts)

• Import provider's stream function and options type
• Add credential detection in getEnvApiKey()
• Add case in mapOptionsForApi() for SimpleStreamOptions mapping
• Add provider to streamFunctions map

4. Model Generation (packages/ai/scripts/generate-models.ts)

• Add logic to fetch/parse models from provider source
• Map to standardized Model interface

5. Tests (packages/ai/test/)

Add provider to: stream.test.ts, tokens.test.ts, abort.test.ts, empty.test.ts, context-overflow.test.ts, image-limits.test.ts, unicode-surrogate.test.ts, tool-call-without-result.test.ts, image-tool-result.test.ts, total-tokens.test.ts, cross-provider-handoff.test.ts.

For cross-provider-handoff.test.ts, add at least one provider/model pair. If the provider exposes multiple model families (for example GPT and Claude), add at least one pair per family.

For non-standard auth, create utility (e.g., bedrock-utils.ts) with credential detection.

6. Coding Agent (packages/coding-agent/)

• src/core/model-resolver.ts: Add default model ID to DEFAULT_MODELS
• src/cli/args.ts: Add env var documentation
• README.md: Add provider setup instructions

7. Documentation

• packages/ai/README.md: Add to providers table, document options/auth, add env vars
• packages/ai/CHANGELOG.md: Add entry under ## [Unreleased]

Releasing

Lockstep versioning: All packages always share the same version number. Every release updates all packages together.

Version semantics (no major releases):

• patch: Bug fixes and new features
• minor: API breaking changes

Steps

1. Update CHANGELOGs: Ensure all changes since last release are documented in the [Unreleased] section of each affected package's CHANGELOG.md

2. Run release script:

   npm run release:patch    # Fixes and additions
   npm run release:minor    # API breaking changes
   

The script handles: version bump, CHANGELOG finalization, commit, tag, publish, and adding new [Unreleased] sections.

CRITICAL Tool Usage Rules CRITICAL

• NEVER use sed/cat to read a file or a range of a file. Always use the read tool (use offset + limit for ranged reads).
• You MUST read every file you modify in full before editing.

CRITICAL Git Rules for Parallel Agents CRITICAL

Multiple agents may work on different files in the same worktree simultaneously. You MUST follow these rules:

Committing

• ONLY commit files YOU changed in THIS session
• NEVER use git add -A or git add . - these sweep up changes from other agents
• ALWAYS use git add <specific-file-paths> listing only files you modified
• Before committing, run git status and verify you are only staging YOUR files
• Track which files you created/modified/deleted during the session

Forbidden Git Operations

These commands can destroy other agents' work:

• git reset --hard - destroys uncommitted changes
• git checkout . - destroys uncommitted changes
• git clean -fd - deletes untracked files
• git stash - stashes ALL changes including other agents' work
• git add -A / git add . - stages other agents' uncommitted work

Safe Workflow

# 1. Check status first
git status

# 2. Add ONLY your specific files
git add packages/ai/src/providers/transform-messages.ts
git add packages/ai/CHANGELOG.md

# 3. Commit
git commit -m "fix(ai): description"

# 4. Push (pull --rebase if needed, but NEVER reset/checkout)
git pull --rebase && git push

If Rebase Conflicts Occur

• Resolve conflicts in YOUR files only
• If conflict is in a file you didn't modify, abort and ask the user
• NEVER force push