8.0 KiB

Raw Blame History

Execution Plan

Current Medium Branch

Branch: MV shot-image production for later video assembly.
Format: 16:9 horizontal.
Production mode: image assets first; video generation/editing remains manual or semi-manual until explicitly automated.
Prompt ownership: Codex owns final image prompts; GPT intake is source specification, not final prompt.

Current Execution Focus

Prepare the execution base, not the full MV.

Immediate focus:

Build and validate the character anchor board.
Build and validate the style anchor board.
Use both anchors in a small visual test package.
Only after tests pass, expand into broader shot production.

Materialization Targets

Target	Required Output	Status
Character anchor board	Main 16:9 board on shallow gray-white background	accepted v2
Character transparent slices	Front full body, side full body, back full body, walking side, walking back	accepted v2-from-anchor set
Character labels	Short identity, clothing, prop, and boundary labels	pending
Style anchor board	16:9 dark-gray board with A/B/C/D samples	accepted
C style retest	Dark muddy puddle / broken star reflection sample	accepted
Shot test package	S-01, S-10, S-46, S-47, S-51	accepted

Small-Batch Strategy

Do not generate all 51 shots first.

Round 1 uses five shots because they test the system's biggest risks:

Shot	Why It Is In Round 1	Anchor
S-01	Opening landscape: proves world-before-person and main A composition.	A
S-10	Steel canyon: proves city pressure without tech/UI drift.	B
S-46	Muddy starlight: proves the soul image and C repair.	C
S-47	Night road fire: proves restrained near-fire transition after C.	D
S-51	Final wide: proves distant fire, no victory, no gathering, person remains small.	D

Round 1 success means these are true:

The traveler stays recognizable without becoming a portrait subject.
A/B/C/D feel like one MV, not four unrelated styles.
C is no longer sunrise/pretty reflection and has clear muddy starlight.
D is warm but not camping, gathering, or victory.
The output can support later prompt batching without rewriting the visual system.

Current Round

Round: R2 five-shot trial preparation.
R0 completed: intake cleaned; project execution files initialized.
R1 completed so far: v2 main character anchor accepted; identity lock approved for slice generation; five transparent slice candidates generated and rejected due identity drift from v2.
R1 completed: v2 main character anchor accepted; v2-from-anchor transparent slice set accepted.
R1 completed: C style retest accepted as style-anchor-c-repair-v1.png.
R1 completed: common style anchor board accepted as style-anchor-board-v1.png.
R2 completed: S-01 generated once and accepted by user.
R2 completed: user waived intermediate prompt review for S-10; S-10 generated once and accepted by user.
R2 completed: S-46 generated once and accepted by user.
R2 completed: S-47 generated once and accepted by user.
R2 completed: S-51 generated once and accepted by user.
R2 completed: five-shot visual trial generated and accepted by user.
R3 character-consistency workflow test completed: s21-v3, s14-v2, and s25-v2 generated through the Advisor / visible-reference path and accepted by user. Quality route is usable; duplicate Agent S-14 remains a historical mechanism defect from this run.
R3 third-round workflow test completed: session-04 generated s33-v2 and s06-v2 through a clean user-visible child session plus internal one-shot SubAgents. Both images were accepted by user; review files were absent as requested; no duplicate-worker defect was observed in this two-slide scope.
R4 completed visually with mechanism warnings: clean child session 019ef8cf-4ab1-7b41-877b-979dc25b0a76 generated s02-v2, s03-v2, and s04-v2; user accepted all three images and review files were absent as requested. Mechanism is not a clean pass because brief/packet files were written by slide Agents rather than prewritten by the visible child session; S-04 also has a worker-launch sequencing warning.
R5 brief-ownership test completed: clean child session 019ef907-16b7-7a43-9924-227892aa62d3 generated accepted s07-v2, s08-v3, and s09-v2 with child-owned brief/packet before worker launch for successful outputs. s08-v2 remains incomplete transport-failure evidence and was retried append-only as s08-v3.
Package-size trials completed through a user-authorized 4-slide package. session-07 produced accepted s11-v2, s12-v2, and s13-v2 with observed context 157K and elapsed time 30m5s. session-08 mechanically completed s15-v2 through s18-v2, but s16-v2 failed visual acceptance because it did not achieve 横向大远景，路从画面一侧切向远方，人物极小 and was too similar to s15.

Active Batch

Polling-based process trial is complete. Broad generation waits for the next user decision after R6 notification/wakeup test design.

No single-shot gate is active. The five-shot visual trial is accepted. The character-consistency workflow test is visually accepted for S-21, S-14, S-25, S-33, S-06, S-07, S-08, S-09, S-11, S-12, and S-13. R4 images for S-02, S-03, and S-04 are visually accepted but remain a mechanism-warning run because child-session brief ownership did not match the desired boundary. R5 successful outputs passed the child-owned brief/packet rule. S-16/s16-v2 is not visually accepted and should be redone later as append-only repair.

Current broad-run issue report:

slides/broad-generation-self-audit-v1.md

Open Decisions

Decision	Default
Character source face	Current stage does not use the real face; use a 50-year-old traveler based on the defined character system.
Character board size	16:9 page, shallow gray-white background.
Character board scope	MVP can start with front/side/back full body plus half-body state; full version should add walking side/back and prop breakdowns.
Style board scope	MVP one-page A/B/C/D board; C should be marked as repaired / accepted.
Full shot production	Wait for next user decision after R6 notification/wakeup test. Current default route: per-shot brief/prompt trace restored, visible character shots use actual references, child sessions may handle up to 3 slides by default unless explicitly overridden, clean user-visible child sessions for orchestration, visible child writes brief/packet before worker launch, internal one-shot SubAgents for slide work, one slide/version has exactly one owning worker, and child sessions perform the completion gate before handoff.

Next Decision

R6 notification/wakeup test:

Replace polling with a notification/wakeup mechanism if the current Codex tools support it: the main session sends the task and exits, then the child session completion activates or wakes the main session.
Do not simulate notification by hidden parent polling. If no real activation/wakeup tool exists, report that as a mechanism blocker.
Use R6 to redo S-16 as append-only s16-v3 or the next unused version.
Required S-16 visual correction: horizontal extreme wide shot; road cuts from one side of the frame toward the distance; traveler is extremely small; result must clearly differ from S-15.
Keep the quality route: gpt-image-2 Advisor prompt/spec, active style master, active character registry when needed, and visible reference images loaded before generation.
Keep the brief ownership rule: the visible child session writes and confirms sNN-vN-brief.md and the slide-agent packet before launching a one-shot slide worker.
Keep append-only retry behavior: incomplete outputs such as s08-v2 remain historical evidence and retries use the next unused version.
Keep the duplicate-worker guard: one successful slide/version must have exactly one owning worker and one prompt/image/return target set.
Keep main-session production behavior lightweight: read child handoff by default after notification/wakeup, and inspect details only on warning/blocked/failed.

8.0 KiB Raw Blame History