diffusionpi 0.2.0

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Onur Solmaz
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/README.md

@@ -0,0 +1,138 @@
+# diffusionpi
+
+Watch a diffusion LLM denoise its answer live in the terminal. diffusionpi
+runs [Pi](https://github.com/earendil-works/pi) against a local vLLM serving
+DiffusionGemma and renders the model's real intermediate canvas above the
+editor: instead of text appearing in silent bursts, you see accepted tokens
+and renoise tokens converge into the final text on every denoising step.
+
+No forked Pi involved: this is a declarative
+[pi-factory](https://github.com/dutifuldev/pi-factory) app bundle plus
+ordinary Pi extensions.
+
+```
+bin/diffusionpi                   launcher (pi-factory wrapper)
+app/                              pi-factory app bundle
+  pi-factory.toml                 interactive session
+  demo.pi-factory.toml            self-driving demo (no tools, auto prompts)
+  extensions/diffusion-canvas.ts  the live canvas widget
+  extensions/smooth-scroll.ts     gradual viewport scroll (Pi internals hack)
+  prompts/                        demo prompts
+docs/diffusion-canvas-repro.md    full reproduction guide
+```
+
+The self-driving demo driver and minimal demo chrome come from the shared
+[pi-demo-mode](https://github.com/osolmaz/pi-demo-mode) extension, an npm
+dependency installed automatically.
+
+## Install
+
+```bash
+npm install -g github:osolmaz/diffusionpi
+```
+
+That puts `diffusionpi` on your PATH. Alternatively clone the repo and run
+`bin/diffusionpi` directly; the launcher fetches its npm dependency on first
+run.
+
+## Requirements
+
+- Node 20+ and npm (Pi and pi-factory are fetched via `npx`).
+- A vLLM server with the diffusion canvas side channel. The changes are pure
+  Python, so they overlay the official precompiled kernels:
+
+  ```bash
+  VLLM_USE_PRECOMPILED=1 \
+  VLLM_PRECOMPILED_WHEEL_COMMIT=4e5ca89cfe98121642d76b40e32a006f4d0fbf3b \
+  pip install git+https://github.com/osolmaz/vllm@canvas-v0.23.1rc4
+  ```
+
+## Run
+
+Serve DiffusionGemma with canvas streaming:
+
+```bash
+vllm serve nvidia/diffusiongemma-26B-A4B-it-NVFP4 \
+  --host 127.0.0.1 --port 8000 \
+  --max-model-len 32768 --max-num-seqs 16 --max-num-batched-tokens 8192 \
+  --kv-cache-dtype fp8 \
+  --enable-auto-tool-choice --tool-call-parser gemma4 \
+  --diffusion-stream-canvas
+```
+
+Then:
+
+```bash
+diffusionpi         # interactive session with the canvas
+diffusionpi demo    # self-driving story demo (for recordings)
+diffusionpi plan    # print the launch plan without running
+```
+
+The launcher turns the bundle in `app/` into a Pi launch: provider `vllm` at
+`http://127.0.0.1:8000/v1`, model `nvidia/diffusiongemma-26B-A4B-it-NVFP4`,
+and the extensions. Edit `app/pi-factory.toml` if your server or model id
+differ.
+
+The canvas widget needs no configuration: it derives the events and metrics
+URLs from the active model's `baseUrl`, with `PI_DIFFUSION_CANVAS_EVENTS_URL`
+and `PI_DIFFUSION_CANVAS_METRICS_URL` as overrides. Against a server without
+the side channel it falls back to a clearly labeled simulation paced by the
+real commit bursts.
+
+## Demo grid and recording
+
+A wall of concurrent diffusionpi sessions (and an mp4 of it) is a job for
+[demowall](https://github.com/osolmaz/demowall), a generic tool that runs N
+copies of any command in a tiled tmux grid and records tmux sessions in a
+themed Ghostty window:
+
+```bash
+# 2x2 wall of self-driving demo sessions:
+demowall grid --concurrency 4 --start -- diffusionpi demo
+
+# Record the wall to an mp4 in a Catppuccin-themed Ghostty window:
+demowall record --session demowall-<timestamp> --out demo.mp4 --seconds 60
+```
+
+Concurrency above 4 needs `--allow-high-concurrency` and should match the
+vLLM server's `--max-num-seqs`.
+
+## Smooth scroll
+
+Stock Pi appends a whole diffusion commit (~15+ lines) to the chat in one
+frame, which makes the viewport jump. The bundled `smooth-scroll` extension
+fixes this with a deliberate hack: it grabs the live TUI instance and wraps
+the chat container's `render()` so appended lines are revealed at a bounded
+rate (default 40 lines/s) instead of all at once. Real content, paced only at
+the render layer.
+
+Because it reaches into Pi internals, it is version-sensitive: it checks that
+the component tree looks like Pi 0.8x and silently no-ops otherwise, so a Pi
+upgrade degrades to the stock jumpy behavior rather than breaking.
+
+- `DIFFUSIONPI_SMOOTH_SCROLL=0` disables it
+- `DIFFUSIONPI_SCROLL_SPEED=<lines/s>` changes the reveal rate
+- `DIFFUSIONPI_SCROLL_DEBUG=<path>` logs per-frame pacing decisions
+
+Independently, you can also make the commits themselves smaller and more
+frequent server-side:
+
+```bash
+vllm serve ... --diffusion-config '{"canvas_length": 64}'
+```
+
+Smaller canvases trade some throughput for gentler commits.
+
+The canvas widget also works in any plain Pi setup, no bundle needed: it is a
+single self-contained extension file, so copy
+[`app/extensions/diffusion-canvas.ts`](app/extensions/diffusion-canvas.ts)
+into your Pi extensions directory (e.g. `~/.pi/agent/extensions/`) or pass it
+with Pi's `--extension` flag.
+
+See [docs/diffusion-canvas-repro.md](docs/diffusion-canvas-repro.md) for the
+full reproduction guide, including how the truthful streaming path works and
+how the vLLM fork is maintained.
+
+## License
+
+[MIT](LICENSE)

package/app/demo.pi-factory.toml

@@ -0,0 +1,36 @@
+id = "diffusionpi"
+name = "DiffusionPi"
+version = "0.1.0"
+schema_version = 1
+description = "Pi + DiffusionGemma with a live diffusion canvas (self-driving demo)"
+state_dir = "~/.local/state/diffusionpi"
+# Same launch as pi-factory.toml plus flags for an unattended demo: no tools
+# (nothing to approve, no accidental tool calls) and no approval prompts.
+pi_command = "npx -y @earendil-works/pi-coding-agent@latest --no-tools --no-approve"
+thinking = "medium"
+
+[provider]
+id = "vllm"
+base_url = "http://127.0.0.1:8000/v1"
+api = "openai-completions"
+
+[model]
+id = "nvidia/diffusiongemma-26B-A4B-it-NVFP4"
+name = "DiffusionGemma 26B-A4B NVFP4"
+context_window = 32768
+max_tokens = 8192
+reasoning = true
+
+[env]
+PI_DEMO_MODE = "1"
+
+[[extensions]]
+path = "extensions/diffusion-canvas.ts"
+
+# Shared self-driving demo extension (npm dependency of the bundle; the
+# launcher installs it on first run and points the prompt files at ../prompts).
+[[extensions]]
+path = "../node_modules/pi-demo-mode/extensions/demo-mode.ts"
+
+[[extensions]]
+path = "extensions/smooth-scroll.ts"