Full README/docs/index.md rewrite from a product/UX-first structure
(what-is-this, why, then a deep-dive per node group with screenshots)
instead of an incremental changelog-style read.
All screenshots regenerated from a real, running ComfyUI instance —
not reused. This surfaced and fixed two more bugs in
scripts/take_screenshots.py, the project's own screenshot-automation
tool, which nobody had run since before the ADR-007 rename (the old
committed screenshots still showed pre-rename node names, e.g.
"Ollama Chat Completion" instead of "Chat Completion"):
- Every LiteGraph.createNode() call used the pre-rename node type
strings (OllamaChatCompletion/OllamaLoadModel/OllamaUnloadModel);
fixed to the current names.
- The canvas locator ("canvas#graph-canvas, canvas") silently
grabbed a 250x200 minimap canvas ComfyUI's frontend added since
this script was last verified, instead of the real graph — every
screenshot failed with a clipping error. Fixed to target
#graph-canvas explicitly.
Two new scenes added, addressing the actual gap: existing
screenshots showed connectivity and options, never the two things
this whole epic sequence was about — structured output (the live
dynamic output sockets appearing as output_schema is edited, via the
real js/ollama.js widget callbacks the previous commit fixed) and
llama.cpp (LlamaCppClient wired into the same generic ChatCompletion
node Ollama uses — the actual point of the adapter pattern).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0132ojafeazQ3ephcBejEWFj
OllamaChatCompletion grew taller with the new timeout_secs widget.
Nodes repositioned with generous horizontal gaps (60→380→720→1200)
and scale reduced to 0.72 so the full Load→Chat→Unload chain is
visible without overlap.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RWysE6jYn4YjNorLBQ1cXb
OllamaUnloadModel now works as a pass-through node: wire
OllamaChatCompletion.response into the optional `passthrough` input and
OllamaChatCompletion.model_name into `model` — ComfyUI's data-flow graph
then guarantees Load → Chat → Unload execution order.
OllamaChatCompletion gains an optional `model_name` forceInput so
OllamaLoadModel.model_name can wire in (creating Load → Chat ordering) and
overrides the COMBO dropdown. It also returns `model_name` as a 3rd output
so the model can flow downstream to UnloadModel without duplication.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RWysE6jYn4YjNorLBQ1cXb
Fresh Playwright sessions landed on ComfyUI's template gallery (no `workflow`
key in localStorage) instead of the node canvas. Pre-seeding an empty workflow
via Playwright storage_state fixes the capture. Also shows localhost:11434 in
the OllamaClient screenshot (user-facing default) rather than the Docker-internal
routing URL.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RWysE6jYn4YjNorLBQ1cXb
Replace hand-crafted PowerPoint exports with Playwright-generated screenshots
taken from the actual running Docker test harness:
- scripts/take_screenshots.py: headless Chromium via Playwright; creates nodes
programmatically via LiteGraph/window.app, triggers updateNodeConfig() for
FormatString's dynamic socket update, then crops tightly around each node
- docs/assets/: four screenshots (fstring, jinja2, random, circuit_breaker)
replacing the old 1920×1080 PowerPoint exports (90%+ smaller, more accurate)
- Justfile: add `screenshots` recipe (starts harness if needed, waits healthy,
runs the script)
- README.md: rewrite to cover all three nodes including Circuit Breaker;
fix stale dependency list (was listing rich/colorama/termcolor which we
removed in spec 001); add ComfyUI Manager install path
- pyproject.toml + uv.lock: add playwright to [dev] dependencies
Run: just screenshots
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RWysE6jYn4YjNorLBQ1cXb
