Every ChatCompletion node in ltx-i2v-pipeline.json now reads its options
through a new OllamaOptionDisableThinking node (id 18, disable_thinking=True)
appended to the end of the existing max-tokens/extra-body chain. Without it,
a thinking-capable model routinely burns its whole max_tokens budget on
chain-of-thought and never emits the closing JSON, so chat_structured fails
validation against an empty string — confirmed live against
saracen9/amoral-qwen3.5-9b. README's thinking-headroom section updated to
match: thinking off by default, headroom advice now framed as what to do if
you deliberately re-enable it via node 18.
Claude-Session: https://claude.ai/code/session_01YArD9ZjBWKsAvazmS48amA
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Wires the 6-agent prompt-compiler pipeline from
project-management/Work/planning/ltx.md onto comfydv's existing generic
LLM nodes (OllamaClient, ChatCompletion, FormatString) — no new node code,
purely a wiring exercise. Verified end-to-end against a live local Ollama
server through the actual ComfyUI node graph (all 6 agents plus the final
judge/refiner output), which is what surfaced and validated the fixes in
the preceding commit.
workflows/README.md documents the deliberate adaptations from the
reference design (single-round Judge/Refiner since ComfyUI graphs can't
express the retry loop, JSON-string list handling for FormatString's
STRING-only dynamic sockets, etc.) and how the wiring was verified against
the real node source before ever touching a live server.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YArD9ZjBWKsAvazmS48amA
