Skip to content

feat(skills): add pi package compatibility skill - #4

Open
nsluss wants to merge 2542 commits into
mainfrom
feat/pi-package-compat-skill
Open

feat(skills): add pi package compatibility skill#4
nsluss wants to merge 2542 commits into
mainfrom
feat/pi-package-compat-skill

Conversation

@nsluss

@nsluss nsluss commented Mar 16, 2026

Copy link
Copy Markdown
Contributor

Summary

Adds a skill documenting how to install pi packages (from the @mariozechner namespace) in punkin by creating symlink aliases.

Problem

Pi packages on npm import from @mariozechner/pi-* but punkin uses @punkin-pi/*, causing module-not-found errors.

Solution

The skill documents creating symlinks to alias the package namespaces:

ln -sf /path/to/punkin/packages/tui node_modules/@mariozechner/pi-tui
ln -sf /path/to/punkin/packages/coding-agent node_modules/@mariozechner/pi-coding-agent
ln -sf /path/to/punkin/packages/ai node_modules/@mariozechner/pi-ai

Includes

  • Trigger phrases for skill activation
  • Step-by-step aliasing instructions
  • One-liner command
  • pi-mcp-adapter worked example
  • MCP configuration setup (mcp.json and ~/.pi/agent symlink)

Testing

Tested with npm:pi-mcp-adapter - /mcp command works after aliasing.

badlogic and others added 30 commits February 5, 2026 20:42
- Add adaptive thinking mode (type: 'adaptive') for Opus 4.6+
- Add effort parameter ('low', 'medium', 'high', 'max') for adaptive thinking
- thinkingEnabled now auto-detects: adaptive for 4.6+, budget-based for older
- streamSimple/completeSimple map ThinkingLevel to effort levels for Opus 4.6
- Add tests for Opus 4.6 adaptive thinking and GPT-5.3 Codex
- Update @anthropic-ai/sdk to 0.73.0
- Update @aws-sdk/client-bedrock-runtime to 3.983.0
- Update @google/genai to 1.40.0
- Remove fast-xml-parser override (no longer needed)
- anthropic: claude-opus-4-5 → claude-opus-4-6
- openai-codex: gpt-5.2-codex → gpt-5.3-codex
- amazon-bedrock: us.anthropic.claude-opus-4-20250514-v1:0 → us.anthropic.claude-opus-4-6-v1:0
- vercel-ai-gateway: anthropic/claude-opus-4.5 → anthropic/claude-opus-4-6
- opencode: claude-opus-4-5 → claude-opus-4-6
…and add EU profile

- Remove :0 suffix from Opus 4.6 Bedrock model IDs (not valid for this model)
- Fix us/eu Opus 4.6 cache pricing (0.5/6.25 instead of 1.5/18.75)
- Add missing eu.anthropic.claude-opus-4-6-v1 inference profile
- Fix coding-agent default Bedrock model ID to match catalog
…tings extensions paths

collectAutoExtensionEntries now checks if the directory itself has a
package.json with pi.extensions (or index.ts) before scanning children.
This fixes duplicate extension loading when a manifest-aware directory
is specified directly in settings.json extensions array.

Fixes #1274
cartazio and others added 28 commits March 7, 2026 18:46
- Sort models: current → favorites → recents → provider order
- Show ★ star indicator for favorite models
- Add Ctrl+F keybind to toggle favorite for selected model
- Display hint for favorite toggle in model selector UI
- Favorites/recents loaded from SettingsManager on mount
- Add temperature and top-p dropdowns to /settings
- Add interleaved thinking and context 1M toggles
- Fix model selector favorite toggle to preserve selection
- Wire settings changes through to Agent at runtime
Interleaved thinking should always be on - not a user choice.
Logs stream lifecycle events to stderr when enabled:
- Stream start/end
- Event counts
- stop_reason from API
- Retry attempts
- Error paths
Anthropic/OpenRouter occasionally return empty responses after tool results.
- Retry with random jitter (up to 1s) to avoid thundering herd
- Configurable via settings: maxEmptyRetries (default: 3), maxEmptyRetryTimeMs (default: 15s)
- Convert to error after limits exhausted - empty is never valid
Added to all three auth paths (API key, OAuth, Copilot):
- Connection: close header to force server to close connection
- fetchOptions: { keepalive: false } to prevent client-side connection pooling

This should prevent connection reuse bugs that may cause empty responses.
Covers OpenRouter and all OpenAI-compatible providers.
…pection CLI

Bug fixes:
- max_tokens: read per-model limits from ~/.agent/settings.toml
  [modelMaxTokens.anthropic] instead of hardcoded model.maxTokens/3
  (~1.3K). Fallback: 128K for Opus 4.6, 64K for all others.
  max_tokens is a per-turn output cap, not context window.
- budget_tokens: only set when explicitly configured via
  thinkingBudgetTokens. Was silently defaulting to 1024 (minimum),
  starving the model of thinking capacity.
- Wire maxEmptyRetries/maxEmptyRetryTimeMs from AgentOptions through
  to AgentLoopConfig for empty response retry control.

New features:
- --dump-settings-template: print ~/.agent/settings_template.toml
- --promote-settings: print effective merged settings as TOML candidate
- SettingsManager.getResolvedSettings(): expose merged settings

Files: agent.ts, anthropic.ts, args.ts, settings-manager.ts, main.ts
Documents how to install pi packages (from @mariozechner namespace) in punkin
by creating symlink aliases from @mariozechner/* to @punkin-pi/* packages.

Includes:
- Problem description (package namespace mismatch)
- Step-by-step solution with symlink aliasing
- One-liner command for quick setup
- pi-mcp-adapter example
- MCP configuration setup
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.