feat: add generated scene skill platform hardening

This commit is contained in:
木炎
2026-04-21 23:19:06 +08:00
parent 118fc77935
commit 956f0c2b68
439 changed files with 61974 additions and 3645 deletions

View File

@@ -0,0 +1,71 @@
# G6 Host-Bridge Entry Readiness Plan
> Date: 2026-04-19
> Status: Draft
> Upstream Spec: [2026-04-19-g6-host-bridge-entry-readiness-design.md](D:/data/ideaSpace/rust/sgClaw/claw-new/docs/superpowers/specs/2026-04-19-g6-host-bridge-entry-readiness-design.md)
## Plan Intent
This plan executes one bounded next slice:
`G6 host-bridge entry readiness`
## Scope Guardrails
1. do not execute a `G6` real sample
2. do not implement host-runtime directly
3. do not open `G8`
4. do not reopen `G7`
5. do not open `G4 / G5`
## Workstreams
1. `WS1` Freeze entry-readiness scope
2. `WS2` Define bounded readiness criteria
3. `WS3` Publish one bounded readiness result
## Phase 0: Freeze the Boundary
### Objective
Lock the plan to entry-readiness only.
### Tasks
1. freeze `G6` as the only target
2. freeze implementation and real execution as out of scope
### Acceptance Criteria
1. no broader host-runtime work begins under this plan
## Phase 1: Define Readiness Criteria
### Objective
Turn the explicit callback verification model into bounded entry-readiness criteria.
### Tasks
1. define which semantics are required before `G6` entry can open
2. define which semantics remain optional
3. define the minimal readiness threshold
### Acceptance Criteria
1. entry-readiness criteria are explicit and bounded
## Phase 2: Publish the Bounded Result
### Objective
Turn the readiness model into one bounded next artifact.
### Tasks
1. publish the readiness result
2. if needed, publish the next bounded follow-up plan
### Acceptance Criteria
1. the next step remains narrower than direct host-runtime implementation