# Agent Invocation Packet: Step 0 Structure Revision

## 1. Invocation Identity

- project_id: knowledge-vault
- workflow: viewpoint-discussion-distillation
- stage: Step 0 whole-source gestalt alignment revision after human response
- run_id: 2026-06-05-失望性情感隔离3
- participant_id: whole-source-gestalt-reviewer
- target_participant_name: Whole-Source Gestalt Reviewer
- participant_type: high_context_participant
- canonical_artifact_path: `C:\Users\wangq\Documents\Codex\ccpe-system\agents\agent-specs\whole-source-gestalt-reviewer.agent.md`
- canonical_artifact_version: 0.1 with Knowledge Vault Human-Review Language Rule
- invocation_mode: codex_thread_participant
- packet_type: formal_runtime_participant_revision_invocation

## 2. Canonical Artifact Handling

- should_paste_full_prompt_or_spec: no; same persistent carrier has already read canonical artifact
- prompt_to_send_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\discussions\viewpoint-development\2026-06-05-失望性情感隔离3\invocations\whole-source-gestalt-reviewer\structure-revision-2026-06-07\prompt-to-send.md`
- role_integrity_requirement: preserve Step 0 whole-source gestalt reviewer role
- allowed_wrapper_instructions: incorporate human corrections, read prior analysis, output language-valid revised Step 0
- forbidden_role_changes: do not become topic router, topic doc writer, segmentation worker, therapist, or article writer
- no_simulation_requirement: true

## 3. Invocation Carrier

- carrier_type: codex_thread_participant
- thread_id: 019ea11e-5e74-73a3-bea9-ad62daf8312d
- agent_id:
- persistent_required: true
- resume_or_followup_method: send follow-up prompt to the same Codex child thread
- execution_status: returned_pending_user_confirmation
- strict_invocation_required: true
- simulation_only: false
- source_primary_language: zh-CN
- output_language_policy: mirror_source_primary_language
- human_review_language_requirement: explanatory content must be primarily Simplified Chinese
- human_confirmation_artifact: true
- gate_id_if_applicable: Gate 0 / Step 0 human review revision

## 4. Current Task

Revise the language-valid Step 0 output using the user's explicit corrections and supplemental prior-run context.

This revision remains before Gate 0 acceptance. It must be returned for another user confirmation.

## 5. Input Files

```text
C:\Users\wangq\Documents\Codex\knowledge-vault\diary\2026\2026-06\2026-06-05.md
```

## 6. Context Files

```text
C:\Users\wangq\Documents\Codex\knowledge-vault\discussions\viewpoint-development\2026-06-05-失望性情感隔离3\invocations\whole-source-gestalt-reviewer\language-repair-2026-06-07\returned-output.md
C:\Users\wangq\Documents\Codex\knowledge-vault\discussions\viewpoint-development\2026-06-05-失望性情感隔离2\invocations\whole-source-gestalt-reviewer\returned-output.md
C:\Users\wangq\Documents\Codex\knowledge-vault\discussions\viewpoint-development\2026-06-05-失望性情感隔离3\00-source-map.md
```

## 7. Embedded Inputs

User corrections:

```text
1. 根主题保留入口案例“失望性情感隔离”。它是“破”；后续 I 域、巨人认知升级等是“立”；再后续是具体执行措施、实验原则、措施和实验设计。
2. `家庭三角认知场` 作为实验设计场景所采用的方法论。
3. 后续 worker 优先做广义保真分析，而不是优先 model-mining。
4. CBT、ACT、MCT、MBT、DBT、图式疗法、IFS 等只是巨人方舟不同层面具体使用的工具。
5. topic organization 确认采用“树形主干 + 交叉链接”。
```

Supplemental prior-run corrections:

```text
- “巨人方舟”作为正式模型名；模型建成后，原巨人认知（现在是2.0版）将下线。
- “家庭三角认知场”可以独立抽出为一个模型；同时作为巨人方舟在实践“失望性情感隔离”领域、青少年典型案例场景下所使用的模型。
- 巨人方舟依然是通用模型；具体领域和场景中，不同层会调用不同模型/理论作为该层工具。
- Reality Lab 作为意图-行动-反馈闭环中的动作模块，属于实践领域。
- QPI 是 GL3 问题表征工具。
- 青少年场景中“家庭主因、学校次之、社会再次之”只是简化假设。
```

## 8. Output Contract

Write the revised Step 0 output to:

```text
C:\Users\wangq\Documents\Codex\knowledge-vault\discussions\viewpoint-development\2026-06-05-失望性情感隔离3\invocations\whole-source-gestalt-reviewer\structure-revision-2026-06-07\returned-output.md
```

The output must be primarily Simplified Chinese and must explicitly include:

```text
source_primary_language: zh-CN
output_language_policy: mirror_source_primary_language
human_review_language_requirement: passed
human_confirmation_artifact: true
gate_id_if_applicable: Gate 0 / Step 0 human review revision
human_confirmation_status: pending
```

The revised content must update:

```text
- root topic framing
- break/build/action structure
- status of Giant Ark as formal model name
- relationship between Giant Ark, Giant Cognition 2.0, QPI, Reality Lab, and Family Triangle Cognitive Field
- worker priority: broad fidelity analysis first
- treatment of therapy models as tools under Giant Ark layers
- topic organization: tree spine plus cross-links
- unresolved questions after incorporating the user's answers
```

## 9. Continuity Policy

The same child thread remains the persistent carrier for further correction before Gate 0.

## 10. Session Logging

The main session will record the revised output path and wait for user confirmation.

## 11. Forbidden Actions

Do not:

```text
- enter Gate 0 or confirm on behalf of the user
- create final `01-topic-map.md`
- create `02-material-routing-log.md`
- write topic documents
- perform evidence routing
- extract material units
- claim coverage audit completion
- create writing-workbench handoff
```

## 12. Return Path

```text
C:\Users\wangq\Documents\Codex\knowledge-vault\discussions\viewpoint-development\2026-06-05-失望性情感隔离3\invocations\whole-source-gestalt-reviewer\structure-revision-2026-06-07\returned-output.md
```

## 13. Runtime Acceptance Rule

This revised output can enter another human review only if produced by the recorded persistent Codex child thread, primarily uses Chinese, and preserves `human_confirmation_status: pending`.