The Mindscape of Bro Tsong

Project: The Mindscape of Bro Tsong

Current phase: model_library_mvp

Current subsystem: Model Library / Model Management MVP

1. Project Definition

This project is a file-first MVP for a cognitive model library.

It turns core cognitive models into structured, traceable, callable, and testable model assets.

The first version validates the workflow with two sample models:

• QPI
• Intellectual Archaeology

2. What This Project Is

This project is:

• A model asset library
• A model card system
• A source evidence index
• A regression test container
• A minimal model selection demo foundation
• A foundation for a future question-answering / cognitive processing system

3. What This Project Is Not

This project is not:

• A full model management platform
• A public SaaS product
• A user-facing application
• A complete knowledge graph
• A full RAG system
• A commercial platform
• A multi-user collaboration system
• A complete question-answering system

4. Current MVP Goal

The current MVP tests whether a small number of core cognitive models can be represented as:

• Human-readable model cards
• Machine-readable JSON model specs
• Source article records
• Source evidence excerpts
• Regression test cases
• Minimal selector inputs and outputs

5. First Sample Models

QPI

QPI is a routing model that classifies a user input as:

• Question: lack of information
• Problem: lack of path or method
• Issue: lack of stability, consensus, or dynamic balance

Intellectual Archaeology

Intellectual Archaeology is a deep modeling model that analyzes a topic through multiple depth layers, from surface application to mechanism, purpose, human capability, and philosophical assumptions.

6. Repository Structure

docs/      Project rules, contracts, workflow notes, decisions, non-goals, and handoff templates.
schemas/   JSON Schema files for model specs, source records, source excerpts, and regression cases.
models/    Machine-readable JSON model specifications.
cards/     Human-readable Markdown model cards.
sources/   Source article records and source evidence excerpts.
tests/     Regression cases for model use, misuse, and boundary checks.
selector/  Rule-based selector configuration and examples.
scripts/   Local validation and selector demo scripts.
reports/   Validation reports, extraction notes, and concrete session handoffs.
knowledge_assets/  Stable long-term reusable knowledge distilled from local project artifacts.
ccra_review_bundle/  Per-round Web CCRA / GPT review packages; each round must live in its own dated subdirectory.
local_ccra_reviews/  File-first Local CCRA review runs, including runtime invocation packets, child-session metadata, local review reports, Owner decisions, and action registers.

7. Data Format

The project uses JSON as the machine-readable source format.

Markdown files are used for human-readable model cards and documentation.

8. Validation

All model JSON files should pass the local schema before they are treated as stable.

Validation should check:

• Required fields
• Enum values
• Unique model IDs
• Source article references
• Source evidence references
• Regression test references
• Model/card indexes
• Markdown card required sections
• Regression case coverage

9. Minimal Selector

The selector is not a full AI system.

It is a simple demo that recommends candidate models based on:

• Trigger keywords
• Input type match
• Negative triggers
• Pipeline position
• Selection priority

10. Development Principles

• Keep the MVP small.
• Prefer files over databases.
• Prefer explicit schema over implicit conventions.
• Prefer traceability over automation.
• Prefer testability over expressive writing.
• Do not expand to many models before the sample models are stable.
• Treat model_library_mvp as the current phase, not as a nested project root.

11. Related Projects

• knowledge-vault: source archive, discussion records, and durable upstream documentation.
• ccpe-system: expert-agent, runtime, model, and protocol specification workbench.
• skills-vault: canonical source for reusable automation skills.
• writing-workbench: deep writing production workspace.
• video-workbench: dimensional output workspace for scripts, presentations, and videos.

This repository consumes selected source material and model definitions from the surrounding ecosystem, but it remains the product/system boundary for The Mindscape of Bro Tsong.

See PROJECTS.md for the operative cross-repository boundary map, including request channels for ccpe-system and skills-vault.

12. Current Status

Foundation repair in progress for:

• QPI
• Intellectual Archaeology / 思想考古学

Current foundation assets include:

• GPT plan localization protocol.
• File taxonomy for canonical, generated, review archive, and temporary files.
• Model extraction rules.
• Model card contract.
• Model extraction workflow.
• JSON schemas for model cards, source articles, source excerpts, regression cases, and indexes.
• Machine-readable model index.
• Human-readable card index.
• Validation scripts for model library contracts and card headings.
• Source article and source excerpt indexes.
• Regression cases for model use, boundary behavior, and misuse.
• Rule-based selector configuration and examples.
• A standard-library validation script that writes reports/validation_report.md.
• A standard-library index rebuild/check script that writes reports/index_rebuild_report.md.
• ChatGPT handoff rules.
• Long-term knowledge asset rules and knowledge_assets/ documents, including 09_数据治理与模型调用机制说明.md.

Current QPI and Intellectual Archaeology model contents pass the local contract and remain draft pending product review.

Indexes follow docs/INDEX_MAINTENANCE_PROTOCOL.md: every asset change must synchronize models/model_index.json and cards/card_index.md, and handoff/release points must run a full rebuild or check.

CCRA review packages are archived by round under ccra_review_bundle/round-NN_YYYY-MM-DD_topic/. Do not place new review bundle files directly in ccra_review_bundle/; create or update the current round directory instead.

Files intended for GPT / CCRA upload inside a review bundle should include the round version in the filename, for example _03.2. Raw changed-file zips should also include the round version while preserving source-relative paths inside the archive.

Use the installed bundle-zip Skill for review bundle raw zips. Do not hand-roll source-relative zip creation with PowerShell Compress-Archive when directory paths matter.

Local CCRA first-pass reviews are recorded under local_ccra_reviews/<public-round>/<local-pass>/. They run through a real CCPE Agent Runtime child session and normally use the same-child review_turn plus planning_turn pattern. Local CCRA v0.1.2 requires explicit helper/runtime policies for bundle audit profile, gate execution mode, routing diff policy, and lifecycle scan scope. Local CCRA output is formal local first review, but it does not replace Owner or Web CCRA judgment. Formal Web CCRA bundles do not include the local review report by default.

Round Conductor rules for Round 05 and later trial use are documented in docs/ROUND_AUTOMATION_PROTOCOL.md. The protocol allows Codex to automate Local CCRA orchestration and Chinese findings confirmation, then repair only findings recorded by Owner as accept_for_codex_fix.

13. Next Steps

1. Round 03 is closed after the Round 03.2a CCRA / GPT pass decision.
2. Keep QPI and Intellectual Archaeology at draft / B / pending until Owner / CCRA review accepts stronger status.
3. Round 04.1 is closed after GPT review acceptance and closeout documentation. The closeout records R04-BI-022 as an accepted collateral depth-limited QPI override and adds it to regression.
4. Round 05 should start from Owner / Web CCRA planning, then use docs/ROUND_AUTOMATION_PROTOCOL.md for the project-local Round Conductor flow.
5. Do not treat Round 04.1 closure as a model lifecycle upgrade or as a predefined Round 05 scope.
6. Defer any third-model expansion until the current QPI selector and case layer are accepted.
7. Route missing reusable extraction, inspection, or stability-scoring tools to requirements/skills-vault/ or requirements/ccpe/ instead of improvising local platform features.