61 lines
2.2 KiB
Markdown
61 lines
2.2 KiB
Markdown
# Agent Invocation Packet: whole-source-gestalt-reviewer
|
|
|
|
## 1. Invocation Identity
|
|
|
|
```text
|
|
participant_id: whole-source-gestalt-reviewer
|
|
workflow: viewpoint-discussion-distillation
|
|
workspace: discussions/viewpoint-development/2026-06-05-失望性情感隔离2
|
|
source_document_path: diary/2026/2026-06/2026-06-05.md
|
|
invocation_mode: real high-context sub-session
|
|
main_session_may_simulate: false
|
|
date: 2026-06-06
|
|
```
|
|
|
|
## 2. Task
|
|
|
|
Read the full source document and produce a Step 0 whole-source gestalt alignment report.
|
|
|
|
The goal is not to route material or draft topic docs. The goal is to align the global structure before segmentation.
|
|
|
|
## 3. Required Output Path
|
|
|
|
```text
|
|
invocations/whole-source-gestalt-reviewer/returned-output.md
|
|
```
|
|
|
|
## 4. Output Contract
|
|
|
|
```text
|
|
- participant identity and invocation metadata
|
|
- source document path and source version note
|
|
- coherence judgment: coherent / mixed / fragmented
|
|
- coherence rationale and split recommendation if mixed or fragmented
|
|
- recommended downstream mode: structure-first / macro-topic split / flat-discovery
|
|
- global topic portrait
|
|
- main structure or candidate layers
|
|
- core tensions and governing questions
|
|
- model-evolution line
|
|
- parent/child/tool/case/action-layer distinctions
|
|
- chunk-first distortion risks
|
|
- segmentation guidance for downstream workers
|
|
- worker lens recommendation: required / partial / omitted
|
|
- confidence notes and unresolved structure questions
|
|
- human confirmation status: pending
|
|
```
|
|
|
|
## 5. Known Prior Distortion Risks
|
|
|
|
The previous pre-gestalt run is retained only as a legacy distortion demo. Do not reuse its topic map as authority.
|
|
|
|
Pay special attention to:
|
|
|
|
```text
|
|
- QPI may be a tool inside a metacognitive / I-domain judgment layer, not a top-level topic.
|
|
- Giant Cognition may upgrade into Giant Ark through GL0 strengthening, GL-R, action experiment, and GL4 limitation.
|
|
- Reality Lab / action experiment may be the intervention layer that turns an explanation model into explanation + intervention.
|
|
- adolescent/family material may be a local deepening branch generated from action experiment, with Family Triangle Cognitive Field as a model candidate.
|
|
```
|
|
|
|
These are prior human concerns. Verify and refine them from the full source instead of merely adopting them.
|