mmprompt/README.md
Z User f5575fa678 Scene composition is the gate, not word counts
The skill exists so the LLM writes/rewrites each scene one at a time
with full attention on making it a complete scene composition — not so
it can hit a word target.

Prompts: the word-budget craft bullets are replaced by an 8-element
composition checklist (subject anchor, style anchor, continuity anchor,
blocking, camera, performance, physical texture, exit state) in both the
scene-writer PROMPT B (new SCENE COMPOSITION section) and the single-pass
prompt. Chase the elements, never a number; padding is as much a failure
as a thin one-liner.

Validator: hard word bands (<10s: 150-200, >=10s: 200-300) removed from
plan and fragment checks. Replaced by a thin-scene floor (100/120 words)
that only trips lazy output, plus a new continuity-anchor check — chained
fragments must open inside the previous end_state. No target band, no
upper limit; output lines say so.

SKILL.md/README: goal, Step 2, craft rules, table rows, and example
outputs updated to match. Suite, --check, chained fragment checks all
green.
2026-10-29 19:13:27 +00:00

229 lines
12 KiB
Markdown
Executable File
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# mmprompt
## h3-plan-gate — MiniMax H3 plan-JSON agent workflow + validator
Prompt set and tooling that turn a story idea into the `plan_json_input` JSON for the
**Production Plan** node (`MiniMax H3 Context Loop Plan` / `MiniMax H3 Plan (Modern)`) in
[ComfyUI-MiniMaxH3-Context-Loop](https://github.com/ethanfel/ComfyUI-MiniMaxH3-Context-Loop),
verified against commit `43afeff`. The deliverable is always **one plan JSON with one shot
per scene** — the node renders every shot as its own clip and chains the clips through the
H3 context loop into one continuous multi-clip video, so pasting one `plan.json` and
queuing once is all the rendering takes.
Instead of asking the LLM to emit that whole JSON in one turn, the gate is agent-shaped:
one outline turn, then **the LLM writes each scene one at a time** — a single turn that
exists purely to compose that scene from every element a good scene needs (subject,
style, continuity, blocking, camera, performance, texture, sound, exit state) — and the
scripts **put it all together at the end** into the same plan JSON the single-pass
prompt would have produced, validated before it ever reaches the node. The point is
compositional attention, not word counts: the validator checks structure and trips only
a thin-scene floor, so any scene can be rewritten until its elements are right, then
re-merged without touching the rest.
### Files
| File | Role |
|---|---|
| `SKILL.md` | Agent Skills entry point — this whole folder is a skill. Cline: copy it to `.cline/skills/h3-plan-gate/` (workspace) or `~/.cline/skills/` (global); any Agent-Skills-compatible agent (Claude Code, Cursor, OpenCode, Codex) can load it too |
| `h3_scene_agent_system_prompt.md` | Stage 1 + 2 system prompts: **PROMPT A** (outline planner) and **PROMPT B** (one-scene-per-turn writer with a `_handoff` chain) |
| `h3_plan_assembler_system_prompt.md` | Stage 3 LLM merge prompt — only when you cannot run scripts |
| `h3_plan_json_system_prompt.md` | Single-pass variant (whole plan in one turn) — fastest for 2–4 scene stories |
| `build_plan.py` | Deterministic Stage 3 merger — puts all the scenes together at the end: strips `_handoff`, injects `"prompt_prefix": [""]` + defaults, validates everything before writing `plan.json` |
| `verify_plan_rules.py` | Node-replica validator (final plans *and* per-turn fragments): structure, handoff truth, continuity, thin-scene floor — no word band — with an embedded test suite |
| `count_prompt_tokens.py` | o200k token counter for the prompt fences (needs `pip install tiktoken`) |
| `h3_agent_workflow_examples/` | Worked 3-scene greenhouse-courier run: `outline.json` → `scene_01..03.json` → `plan.json` |
### Agent workflow (3 stages)
**Stage 1 — Outline.** Put PROMPT A (from `h3_scene_agent_system_prompt.md`) in the system
field, the story idea in the user field. Save the reply as `outline.json`. It freezes scene
count, ids, durations, beats, verbatim dialogue distribution, and the `style_and_cast` block
so later turns cannot drift. You may hand-edit it before Stage 2 — the scene agents follow
the edited skeleton.
**Stage 2 — One scene per turn.** Put PROMPT B in the system field and paste this turn
template as the user message:
```text
STORY: <the full story idea>
STYLE AND CAST: <paste the "style_and_cast" object from the outline>
OUTLINE: <paste the "scenes" array from the outline>
WRITE SCENE: 2
PREVIOUS HANDOFF: <paste the previous scene's "_handoff" object — or: This is scene 1.>
```
Save each reply as `scene_NN.json` (zero-padded). Each fragment carries the native H3
three-line prompt (`integrated_multimodal_description: [Shot 1] …` / `overall_soundscape: …`
/ `non_diegetic_music: …`), the full scene composition, and a truthful `_handoff`
object for the next turn. Optional gate after each turn:
```sh
.venv\Scripts\python.exe h3-plan-gate/verify_plan_rules.py fragment scene_02.json --index 2 --prev scene_01.json
```
(All command blocks below use the Windows venv form; on macOS/Linux replace
`.venv\Scripts\python.exe` with `python3`.)
**Stage 3 — Assembly (deterministic, preferred):**
```sh
.venv\Scripts\python.exe h3-plan-gate/build_plan.py outline.json scene_01.json scene_02.json scene_03.json -o plan.json
```
The merger validates every fragment in the `_handoff` chain (against the outline when
present), then validates the merged plan — only clean JSON is written. Do **not** edit
fragment prose by hand during assembly; if you want a scene changed, re-run its Stage 2
turn and re-merge. Use the LLM assembler prompt only in a pure-chat setup with no script
execution, and diff its output against the fragments if you do (small models transcribe
long strings unreliably; `build_plan.py` is byte-exact by construction).
## Example: story idea → final output
The complete run of the shipped example (`h3_agent_workflow_examples/`) — the same files
your agent should produce for any story.
**1. Give Cline the story idea.** With the skill installed, the whole request is:
```text
Use the h3-plan-gate skill. Story: a courier delivers a package to a greenhouse in the
rain, three shots. When he reaches the table he says exactly: Package for the greenhouse,
right on time.
```
**2. The agent runs the smoke test** — proving the toolchain before writing anything:
```sh
.venv\Scripts\python.exe h3-plan-gate/verify_plan_rules.py
.venv\Scripts\python.exe h3-plan-gate/build_plan.py --check h3-plan-gate/h3_agent_workflow_examples/plan.json
```
Expect the suite to pass and, from the second command, `PLAN OK` with
`total delivered: 1042 frames = 43.42s`.
**3. The agent writes `outline.json`** — the skeleton that freezes cast, style, ids,
durations, and dialogue so later scenes cannot drift:
```json
{
"title": "greenhouse_courier",
"defaults": { "duration_seconds": 15, "steps": 20 },
"style_and_cast": {
"subjects": ["<Subject 1> — an adult bicycle courier; mustard-yellow waterproof jacket, dark teal trousers, charcoal helmet, olive messenger bag"],
"style": "Photorealistic overcast rainy daylight, soft grey palette, stable landscape tracking shots at eye level",
"soundscape_seed": "steady light rain drumming on glass roofing, low distant traffic hum"
},
"scenes": [
{ "index": 1, "id": "greenhouse_arrival", "duration_seconds": 15,
"beat": "He wheels his silver bicycle through the greenhouse entrance out of the rain and crosses the interior threshold mid-stride.",
"dialogue": [] },
{ "index": 2, "id": "greenhouse_aisle", "duration_seconds": 15,
"beat": "He pushes the bike down the central aisle toward the potting table and slows it to a crawl, one hand reaching for the bag flap.",
"dialogue": [] },
{ "index": 3, "id": "greenhouse_delivery", "duration_seconds": 15,
"beat": "He sets the kraft parcel on the wooden potting table and speaks his line as the delivery completes.",
"dialogue": ["Package for the greenhouse, right on time."] }
]
}
```
**4. The agent composes each scene one at a time** — one file per turn, each turn
given over to making that one scene a complete composition, validating it before
moving to the next:
```sh
.venv\Scripts\python.exe h3-plan-gate/verify_plan_rules.py fragment scene_01.json --index 1 --total 3
.venv\Scripts\python.exe h3-plan-gate/verify_plan_rules.py fragment scene_02.json --index 2 --total 3 --prev scene_01.json
.venv\Scripts\python.exe h3-plan-gate/verify_plan_rules.py fragment scene_03.json --index 3 --total 3 --prev scene_02.json
```
Each fragment carries the three-line H3 prompt and a truthful `_handoff`. Scene 3
(description elided — the real file carries the full blocking, camera work, wardrobe
behavior, and lighting detail):
```json
{
"id": "greenhouse_delivery",
"duration_seconds": 15,
"prompt": [
"integrated_multimodal_description: [Shot 1] Continue the same forward stride … He stands silently with mouth closed, then speaks. <d>[English] Package for the greenhouse, right on time.</d> He falls silently with mouth closed … End on the calm wide composition as the delivery completes.",
"overall_soundscape: the same rain on glass and wet paving continues, tires creak to a stop, the kraft paper parcel thuds softly on the wooden potting table.",
"non_diegetic_music: N/A"
],
"_handoff": { "end_state": "…", "soundscape": "…", "dialogue_used": ["Package for the greenhouse, right on time."] }
}
```
**5. The agent puts it all together at the end** — merging every scene into one plan
JSON, never writing plan JSON by hand:
```sh
.venv\Scripts\python.exe h3-plan-gate/build_plan.py outline.json scene_01.json scene_02.json scene_03.json -o plan.json
.venv\Scripts\python.exe h3-plan-gate/build_plan.py --check plan.json
```
Output:
```text
outline: outline.json (3 scenes)
fragment 1/3 … fragment 2/3 … fragment 3/3 …
Merged plan:
shot 1 id='greenhouse_arrival' raw=362 delivered=362 steps=20
shot 2 id='greenhouse_aisle' raw=362 delivered=340 steps=20
shot 3 id='greenhouse_delivery' raw=362 delivered=340 steps=20
total delivered: 1042 frames = 43.42s
H3 section structure: all shots have the 3 sections in canonical order
description lengths: ['221w @ 15s', '219w @ 15s', '237w @ 15s'] | composition elements are the gate - no word band
wrote plan.json - paste its full contents into plan_json_input
```
The deliverable is the single `plan.json` — `"prompt_prefix": [""]`, `defaults`, and
three self-sufficient shots: exactly the shape the single-pass system prompt emits (full
file: `h3_agent_workflow_examples/plan.json`).
**6. Render the multi-clip video.** Paste the full contents of `plan.json` into the
Production Plan node's forced STRING input `plan_json_input` and queue **once**. The node
renders each shot as its own clip and chains the clips through the H3 context loop —
scene 2 continues from scene 1's final frames, scene 3 from scene 2's — producing ONE
continuous multi-clip video: 1042 delivered frames ≈ 43.4 s at 24 fps (every scene after
the first loses ~1 second to the fixed overlap trim that stitches the clips together).
Want scene 2 different? Just tell the agent "rewrite scene 2, keep everything else": it
rewrites only `scene_02.json`, re-validates it, and re-merges — refreshing `plan.json`
in one command.
### Validating
```sh
.venv\Scripts\python.exe h3-plan-gate/verify_plan_rules.py # embedded pass/fail suite
.venv\Scripts\python.exe h3-plan-gate/verify_plan_rules.py plan plan.json # node-rule replica on a final plan
.venv\Scripts\python.exe h3-plan-gate/build_plan.py --check plan.json # same checks + frame/duration report
```
Smoke test with the shipped examples:
```sh
.venv\Scripts\python.exe h3-plan-gate/build_plan.py --check h3-plan-gate/h3_agent_workflow_examples/plan.json
# expect: PLAN OK with "total delivered: 1042 frames = 43.42s"
```
### Wiring the result
Paste the full contents of `plan.json` into the Plan node's forced STRING input
**`plan_json_input`** (a non-empty connected value overrides the visual editor's plan for
that run) and queue once — the node's context loop turns the multi-shot plan into one
multi-clip video by itself; no per-scene renders, no editor stitching. Resolution,
context length, audio mode, and `base_seed` stay on the node's own widgets (the JSON
cannot set them; default canvas is 960×544 — set width/height widgets and wire the
width/height outputs into the conditioning node and sampler latent to avoid square
output).
### Requirements
- `build_plan.py` and `verify_plan_rules.py`: Python 3 stdlib only — no venv packages
needed; the `.venv\Scripts\python.exe` form just matches a typical Windows project
layout, and plain `python` / `python3` works anywhere.
- `count_prompt_tokens.py`: needs `tiktoken`.
- LLM settings: temperature 0.3–0.7; enable `response_format: {"type": "json_object"}` or
grammar-constrained JSON if the server supports it. Each scene turn is ≈5k tokens, so
ctx 16384 is comfortable; 128k runs the whole workflow many times over.