track-gate: built-in LLM system prompts are published (BASE/REF guides, selection + delivery rules)

This commit is contained in:
Z User 2026-11-01 04:05:09 +00:00
parent 8a9c79f06e
commit 7b6a2da472

View File

@ -98,3 +98,29 @@ It contains no LLM node; prompts come from the timeline JSON. This is the pack's
agent-driven setup: an external LLM (agent) writes the whole `track_data`, then one agent-driven setup: an external LLM (agent) writes the whole `track_data`, then one
run renders it. The pack even ships `skills/easy-media-multitrack-workflow` + run renders it. The pack even ships `skills/easy-media-multitrack-workflow` +
`patch_workflow.py` for exactly that flow (our SKILL.md step 5B). `patch_workflow.py` for exactly that flow (our SKILL.md step 5B).
## The built-in LLM system prompts (published, not locked)
The rewrite-LLM contract ships in the open in the pack:
`utils/prompt_builder.py` — `MINIMAX_BASE_PROMPT` (~15.7 KB, "Video Prompt Writing
Guide (T2VA / I2VA / FL2VA / L2VA)") and `MINIMAX_REF_PROMPT` (~23.5 KB, "Full-
Reference Mode Rewrite Output Format Guide" — six-section rewrite with
`<Subject N>` / `<Picture N>` / `<Video N>` / `<Audio N>` labels).
Selection (`build_prompt_request`, MiniMax branch):
- `task_mode` `default` / `l2v` (our t2v payloads) → `MINIMAX_BASE_PROMPT`
- `task_mode` `ref` / `edit` → `MINIMAX_REF_PROMPT`
- a non-empty per-segment `system_prompt` overrides both; with an empty one the
context-segment continuity rules ride the MiniMax rewrite API server-side
(entry rule: not-first segment using `context`; tail rule: next segment uses
`context`) — per the pack's own `multitrack-schema.md`.
Delivery: the system prompt only leaves TaskOutput via `prompt_format`
`api` or `llm` (`default` / `promptRelay` output an empty SYSTEM_PROMPT).
`build_llm_prompt` folds system+user into one transcript for single-input LLM
nodes. To use the user's own LLM with the same behavior: paste
`minimax_base_prompt.txt` (or the ref guide for ref-mode work) into the LLM
node's system prompt field and wire TaskOutput SYSTEM_PROMPT/USER_PROMPT into
it — or leave the LLM's system prompt empty and pass TaskOutput.SYSTEM_PROMPT
through, which already carries the selected guide verbatim.