Minimal shell wrapper around llama.cpp router's OpenAI-compatible API
(/v1/chat/completions), gated by the same mTLS cert as the pi extension.
Single-file, runtime deps: bash + curl + jq. Useful for scripts and agents
(Claude Code, etc.) that want to delegate generation without pulling in
a full SDK.
Features:
--list / --status / --load <model>
--stream <model> "..." for SSE token-stream output
--raw <model> '...' for full openai-format json bodies (also @file)
--prompt-file <path> reads prompt from disk via jq --rawfile, bypassing
Linux's MAX_ARG_STRLEN (~128KB per argv) so prompts
up to the model's context window work
--temperature / --top-p / --max-tokens / --system sampling overrides
Auto-retry with exponential backoff on transient empty/non-JSON
responses (model-loading window). Short-circuits on structured 4xx
errors (e.g. exceed_context_size).
AI_CERT_DIR / AI_ENDPOINT / AI_RETRIES env overrides.
Includes scripts/AI-COMPLETE.md with install + usage docs and a row in
the top-level README's scripts table.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
7.0 KiB
pi-extensions
Personal collection of extensions, themes, and scripts for pi — Mario Zechner's CLI coding agent.
The anchor of the repo is ai-server, a multi-file pi extension that lets pi talk to a self-hosted llama.cpp router behind mTLS. Everything else (theme, banner, custom footer, working indicator, session-name generator, etc.) is Warhammer 40k "Dark Mechanicum" flavoring on top of pi's interactive TUI.
Installed extensions
| Extension | What it does |
|---|---|
ai-server/ |
Remote llama.cpp provider over mTLS. Dynamic model discovery. Admin slash commands (load / unload / ctx / preset / restart / refresh). Custom SSE stream implementation with tool calls, reasoning, cache token reporting. See ai-server/README.md for the full setup. |
local-llama.ts |
Tiny provider registration for a local llama-server (e.g. 127.0.0.1:8088). |
dark-mechanicus-indicator.ts |
Replaces pi's default working-indicator with ⚙ <quote> · <elapsed>. ⚙ pulses gold-dim → normal → bright → normal (1s cycle); one of 45 Dark-Mechanicum quotes rotates every 10s; elapsed time ticks every second. |
mechanicus-footer.ts |
Replaces pi's default footer. Context shown as 45k/131k (34%) instead of 34%/131k. Adds compaction counter (C2) and last-turn tok/s. |
mechanicus-status-line.ts |
Third footer line: ⚙ HERETEK FORGE · ACTIVE / SCRAPCODE CIRCUITRY · OPERATIONAL / etc. Rotates each turn. |
mechanicus-banner.ts |
Custom TUI header — cog-and-skull art (LEX HERETEK, SCRAPCODE TRIUMPHS, BLOOD-FORGE ETERNAL) with text block on the left and ASCII cog on the right. |
mechanicus-session-names.ts |
Auto-names new sessions with a random <adjective>-<noun> · <NNN> (e.g. Heretek-Blood-Forge · 042). Mirrors the name into the terminal tab title. |
mechanicus-thinking-label.ts |
Swaps pi's Thinking... fold-label for Cogitating.... |
markdown-body-color.ts |
Monkey-patches pi-tui's Markdown + Editor components so unstyled paragraph text and editor typing text don't inherit the terminal profile's default foreground (often green). Forces a lavender inkPurple body color. |
Theme
| File | Palette |
|---|---|
themes/dark-mechanicus.json |
Dark purple aubergine background (#16101e), AdMech blood-red accents (#a8232c), burnished brass borders (#b8803d), nurgle-green syntax strings (#5a6b2e), cognitor-pink syntax types (#c75a8a). All 51 color tokens defined. |
Activate with /settings inside pi (or set "theme": "dark-mechanicus" in
~/.pi/agent/settings.json). Pi hot-reloads on edits to the active theme file.
Setup scripts
| Script | Runs on | Purpose |
|---|---|---|
scripts/install-client.sh |
New pi client | Bootstraps a client: fetches certs from the Caddy host, rsyncs extensions + themes into ~/.pi/agent/, verifies the mTLS /health endpoint. |
scripts/issue-client-cert.sh |
Caddy host | Generates a new client identity (key + cert + modern + legacy p12) for a named device. Use for each new machine. |
scripts/install-browser-certs.sh |
New client | Imports client cert + root CA into Brave Flatpak NSS, system NSS, Firefox profiles, and optionally the system trust store. Mostly obsolete since the Caddy switch to Let's Encrypt but still useful for the mTLS client cert side. |
scripts/ai-complete (docs) |
Any pi client | Minimal shell CLI for direct llama-server router access. Wraps https://ai.shahondin1624.de/v1/chat/completions with mTLS, with retries, prompt-from-file, streaming, and model load/status helpers. Useful for scripts and agents (Claude Code, etc.) that want to delegate generation. |
Tests
Twenty-eight tests total, no external dependencies. Runs with Node 22+'s
built-in test runner + --experimental-strip-types:
node --experimental-strip-types --test tests/*.test.ts
| File | Coverage |
|---|---|
tests/messages.test.ts |
13 unit tests over ai-server/messages.ts — pi Context → OpenAI payload conversion (system prompts, user/assistant/tool-result roles, tool calls, image-only messages). |
tests/router-utils.test.ts |
9 unit tests over ai-server/router-utils.ts — extractCtxSize, isShardArtefact (the filter that hides GGUF multi-shard phantoms from the model picker). |
tests/integration.test.ts |
6 live-endpoint tests: /health, /models, model-entry shape, mTLS enforcement, publicly-trusted cert (Let's Encrypt contract), chat completion usage shape including prompt_tokens_details.cached_tokens. Auto-skip if the server is unreachable. |
Stream-parsing edge cases (SSE framing, tool-call splits across chunks, reasoning deltas, abort mid-stream) remain deferred — they need a mock HTTPS server harness, not worth the complexity for a one-user setup.
Quick onboarding for another machine
# 1. Mint a new client identity (on the Caddy host)
ssh shahondin1624@192.168.2.2 '~/pi-extensions/scripts/issue-client-cert.sh laptop-alice'
# 2. On the new pi client
git clone https://git.shahondin1624.de/shahondin1624/pi-extensions.git ~/pi-extensions
cd ~/pi-extensions
scripts/install-client.sh
# 3. Activate the theme
# /settings in pi, pick "dark-mechanicus"
Layout
pi-extensions/
├── ai-server/ the core mTLS provider (multi-file extension)
│ ├── index.ts entry — provider + admin commands
│ ├── config.ts URLs, SSH host, cert loading, MODELS[]
│ ├── messages.ts Context → OpenAI messages
│ ├── stream.ts custom SSE stream, mTLS HTTPS, pi-ai events
│ ├── admin.ts router HTTP client + SSH helpers
│ ├── router-utils.ts pure helpers (test-friendly)
│ └── README.md full mTLS + systemd + Caddy setup notes
├── dark-mechanicus-indicator.ts working indicator (cog + quote + timer)
├── mechanicus-footer.ts custom footer layout
├── mechanicus-status-line.ts rotating flavor status line
├── mechanicus-banner.ts TUI header art
├── mechanicus-session-names.ts auto-name generator + tab title
├── mechanicus-thinking-label.ts "Cogitating..." for folded thinking blocks
├── markdown-body-color.ts forces body text color for chat + editor
├── local-llama.ts local llama-server provider
├── themes/
│ └── dark-mechanicus.json 51-token theme
├── scripts/ install helpers
├── tests/ node:test suites
└── README.md this file
License
Personal use. No license declared; the repo is private.