chore: initialize cognitive os m0 m1
This commit is contained in:
commit
4448bf210b
|
|
@ -0,0 +1,59 @@
|
|||
# Agent Instructions
|
||||
|
||||
This repository is the new `Cognitive-OS-Wantsong` project. It is not a continuation of `the-mindscape-of-bro-tsong`.
|
||||
|
||||
Before editing, read:
|
||||
|
||||
1. `README.md`
|
||||
2. `PROJECTS.md`
|
||||
3. `docs/PROJECT_BRIEF.md`
|
||||
4. `docs/ASSET_MIGRATION_POLICY.md`
|
||||
5. `docs/MODEL_MANAGEMENT_V0.md`
|
||||
6. `docs/MODEL_ORCHESTRATION_V0.md`
|
||||
|
||||
## Hard Boundaries
|
||||
|
||||
- Treat the old project only as `model-governance-lab / asset-seed archive / anti-pattern reference`.
|
||||
- Do not bulk-copy old directories or files into this repository.
|
||||
- Do not create `ccra_review_bundle/`.
|
||||
- Do not migrate old `reports/`.
|
||||
- Do not migrate old `local_ccra_reviews/`.
|
||||
- Do not import full regression suites, full selector calibration, lifecycle scan workflows, review-bundle packagers, or Round Conductor.
|
||||
- Do not create sample runs, prompts, examples, or review packets during M0-M1 unless the owner explicitly starts a later milestone.
|
||||
- Do not use `lite` in model filenames.
|
||||
- Do not claim any model is final, accepted, approved, production-ready, or long-term core unless a milestone review explicitly records that decision.
|
||||
|
||||
## M0-M1 Working Rule
|
||||
|
||||
M0-M1 is allowed to define:
|
||||
|
||||
- project boundary;
|
||||
- asset migration policy;
|
||||
- minimal model status and registry rules;
|
||||
- QPI as a routing model;
|
||||
- Intellectual Archaeology as a deep-processing model;
|
||||
- model orchestration fields needed later for primary/support selection.
|
||||
|
||||
M0-M1 is not allowed to run a sample or expand the model set.
|
||||
|
||||
## Model Roles
|
||||
|
||||
Use these role names in model cards and registry entries:
|
||||
|
||||
- `routing_model`
|
||||
- `depth_model`
|
||||
- `primary_model`
|
||||
- `support_model`
|
||||
- `contrast_model`
|
||||
- `calibration_model`
|
||||
- `translation_model`
|
||||
- `synthesis_model`
|
||||
|
||||
Default posture:
|
||||
|
||||
- `qpi` is `routing_model`;
|
||||
- `intellectual_archaeology` is `depth_model` and can become `primary_model` for high-value deep-processing cases.
|
||||
|
||||
## Local CCRA
|
||||
|
||||
Local CCRA is a milestone review lane only. It reviews milestone outputs and scope drift. It does not authorize repairs by itself, and it does not create public Web bundles by default.
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
# Project Operating Notes
|
||||
|
||||
## Active Phase
|
||||
|
||||
Current phase: M0-M1 startup.
|
||||
|
||||
The active deliverable is a small file-first foundation for a cognitive-processing runtime. The repository should stay closer to runtime setup than governance evidence.
|
||||
|
||||
## Source Of Truth
|
||||
|
||||
This repository owns its own project boundary and model registry.
|
||||
|
||||
External materials are reference inputs only:
|
||||
|
||||
- `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\Cognitive-OS-Wantsong项目总计划 v0.1.md`
|
||||
- `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong`
|
||||
- selected Owner-authored cognitive-system source documents in `knowledge-vault`
|
||||
|
||||
The old project is not an upstream branch and not a source tree to merge.
|
||||
|
||||
## Milestone Order
|
||||
|
||||
1. M0: project boundary freeze.
|
||||
2. M1: model-management kernel.
|
||||
3. M2: prompt/runtime skeleton.
|
||||
4. M3: reader translation prompt and before/after translation check.
|
||||
5. M4: first real sample run.
|
||||
6. M5: first Local CCRA milestone review.
|
||||
|
||||
Do not skip from M1 into sample execution without an explicit owner instruction.
|
||||
|
||||
## Supplier Boundaries
|
||||
|
||||
This repository may record requests for external reusable tooling later, but M0-M1 should not create a supplier-request channel unless a real missing tool blocks progress.
|
||||
|
||||
Reusable policy, reviewers, and broader CCRA method should stay outside this product repo unless the owner explicitly asks to localize a milestone protocol.
|
||||
|
||||
## Naming
|
||||
|
||||
Use kebab-case for filenames and directories.
|
||||
|
||||
Use snake_case for registry `model_id` values when the model identity already uses an underscore, for example `intellectual_archaeology`.
|
||||
|
||||
Do not use `lite` suffixes in filenames or model IDs.
|
||||
|
|
@ -0,0 +1,89 @@
|
|||
# Cognitive-OS-Wantsong
|
||||
|
||||
status: m0_m1_startup
|
||||
owner: Wantsong
|
||||
date: 2026-06-20
|
||||
|
||||
## Product Definition
|
||||
|
||||
`Cognitive-OS-Wantsong` is a lightweight, file-first cognitive-processing runtime for Wantsong's personal model system.
|
||||
|
||||
The project goal is not to prove that model files can be governed. The first product question is:
|
||||
|
||||
```text
|
||||
Given a real complex input, can the system chain Wantsong's cognitive models
|
||||
and produce a useful internal cognitive-processing result plus a reader-facing translation?
|
||||
```
|
||||
|
||||
The startup rule is:
|
||||
|
||||
```text
|
||||
First prove cognitive processing.
|
||||
Only then govern the pieces that prove useful.
|
||||
```
|
||||
|
||||
## Current Milestone
|
||||
|
||||
This repository starts at M0-M1 only.
|
||||
|
||||
M0 freezes the project boundary:
|
||||
|
||||
- this is a new git repository, not a continuation branch of `the-mindscape-of-bro-tsong`;
|
||||
- the old project is only an asset-seed archive and anti-pattern reference;
|
||||
- old reports, review bundles, Local CCRA histories, selector calibration, full regression, and Round Conductor workflows are not migrated.
|
||||
|
||||
M1 creates the minimal model-management kernel:
|
||||
|
||||
- `models/qpi.md`;
|
||||
- `models/intellectual-archaeology.md`;
|
||||
- `models/model-registry.json`;
|
||||
- model-management and orchestration rules under `docs/`.
|
||||
|
||||
## Not In Scope
|
||||
|
||||
Do not add these during M0-M1:
|
||||
|
||||
- sample runs;
|
||||
- prompt runners;
|
||||
- frontend or backend service;
|
||||
- database, RAG, vector store, or knowledge graph;
|
||||
- 10-model expansion;
|
||||
- full model lifecycle system;
|
||||
- full selector;
|
||||
- full regression suite;
|
||||
- Web review bundle;
|
||||
- `ccra_review_bundle/`;
|
||||
- old `reports/`;
|
||||
- old `local_ccra_reviews/`;
|
||||
- Round Conductor.
|
||||
|
||||
## Repository Map
|
||||
|
||||
```text
|
||||
README.md
|
||||
AGENTS.md
|
||||
PROJECTS.md
|
||||
docs/
|
||||
PROJECT_BRIEF.md
|
||||
COGNITIVE_WORKFLOW_V0.md
|
||||
MODEL_MANAGEMENT_V0.md
|
||||
MODEL_ORCHESTRATION_V0.md
|
||||
READER_TRANSLATION_LAYER_V0.md
|
||||
LOCAL_CCRA_MILESTONE_PROTOCOL.md
|
||||
ASSET_MIGRATION_POLICY.md
|
||||
DECISIONS.md
|
||||
models/
|
||||
qpi.md
|
||||
intellectual-archaeology.md
|
||||
model-registry.json
|
||||
```
|
||||
|
||||
No model file uses a `lite` suffix. Minimality is expressed inside each model card with `runtime_scope: minimal_v0` and `governance_level: draft_callable`.
|
||||
|
||||
## Operating Posture
|
||||
|
||||
QPI is a front-routing and misframing-diagnostic model. It should not become the main product object again.
|
||||
|
||||
Intellectual Archaeology is the first deep-processing engine. It should be tested through real cognitive processing before expanding the model universe.
|
||||
|
||||
Local CCRA remains available only as a milestone review lane. It is not a default round factory.
|
||||
|
|
@ -0,0 +1,80 @@
|
|||
# Asset Migration Policy
|
||||
|
||||
status: draft_runtime_policy
|
||||
date: 2026-06-20
|
||||
|
||||
## Rule
|
||||
|
||||
Do not migrate directories. Migrate only selected principles or seed content, rewritten into this project's runtime language.
|
||||
|
||||
The old project is:
|
||||
|
||||
```text
|
||||
model-governance-lab
|
||||
asset-seed archive
|
||||
historical reference
|
||||
anti-pattern reference
|
||||
```
|
||||
|
||||
It is not a parent codebase.
|
||||
|
||||
## Allowed Seed Sources
|
||||
|
||||
Allowed only as reference inputs:
|
||||
|
||||
- old QPI model/card material;
|
||||
- old Intellectual Archaeology model/card material;
|
||||
- selected source/excerpt structures;
|
||||
- selected examples after later owner approval;
|
||||
- `Wantsong认知操作系统.md`;
|
||||
- the Intellectual Archaeology seven-layer example report;
|
||||
- selected lessons from old governance explanations.
|
||||
|
||||
## Forbidden Migration
|
||||
|
||||
Do not copy or recreate:
|
||||
|
||||
- old `reports/`;
|
||||
- old `ccra_review_bundle/`;
|
||||
- old `local_ccra_reviews/`;
|
||||
- full QPI regression suite;
|
||||
- full selector calibration;
|
||||
- before/after selector diff workflow;
|
||||
- lifecycle-status scan workflow;
|
||||
- review-bundle packager workflow;
|
||||
- Round Conductor;
|
||||
- old process manifests;
|
||||
- old validation reports as project truth.
|
||||
|
||||
## Knowledge Asset Rule
|
||||
|
||||
Do not create the old-style `knowledge_assets/` directory in v0.1.
|
||||
|
||||
If a legacy principle is useful, rewrite it into one of these docs:
|
||||
|
||||
- `docs/PROJECT_BRIEF.md`;
|
||||
- `docs/MODEL_MANAGEMENT_V0.md`;
|
||||
- `docs/MODEL_ORCHESTRATION_V0.md`;
|
||||
- `docs/LOCAL_CCRA_MILESTONE_PROTOCOL.md`;
|
||||
- `docs/DECISIONS.md`.
|
||||
|
||||
## Rewrite Standard
|
||||
|
||||
A migrated principle must be rewritten so that it answers:
|
||||
|
||||
- how this runtime should process inputs;
|
||||
- when a model should or should not be called;
|
||||
- how output value will be inspected;
|
||||
- how to prevent over-governance;
|
||||
- what owner decision is needed before expansion.
|
||||
|
||||
Do not preserve old round labels, old bundle names, or old review evidence as operating rules.
|
||||
|
||||
## M0-M1 Migration Actually Used
|
||||
|
||||
M0-M1 uses the old project only to compress two seed model cards:
|
||||
|
||||
- `qpi`;
|
||||
- `intellectual_archaeology`.
|
||||
|
||||
No reports, review bundles, Local CCRA histories, full regression suites, selector calibration sets, or lifecycle workflows are migrated.
|
||||
|
|
@ -0,0 +1,95 @@
|
|||
# Cognitive Workflow V0
|
||||
|
||||
status: draft_workflow_contract
|
||||
date: 2026-06-20
|
||||
|
||||
This file describes the intended runtime loop. It is not a sample run and does not authorize M0-M1 to create prompt files or examples.
|
||||
|
||||
## Runtime Flow
|
||||
|
||||
```text
|
||||
1. Intake / Value Assessment
|
||||
2. QPI
|
||||
3. Lens Orchestrator
|
||||
4. Deep Processing
|
||||
5. Synthesis & Calibration
|
||||
6. Feedback & Asset Decision
|
||||
7. Reader Translation
|
||||
```
|
||||
|
||||
## 1. Intake / Value Assessment
|
||||
|
||||
Purpose: decide whether the input deserves cognitive processing and what depth budget is justified.
|
||||
|
||||
Expected output:
|
||||
|
||||
- processing level: `L1 | L2 | L3 | L4`;
|
||||
- reason for depth;
|
||||
- whether heavy processing is justified;
|
||||
- required context gaps.
|
||||
|
||||
## 2. QPI
|
||||
|
||||
Purpose: classify the issue framing before deeper work.
|
||||
|
||||
QPI outputs:
|
||||
|
||||
- `question | problem | issue | mixed | no_call`;
|
||||
- owner and scenario;
|
||||
- dominant scarcity;
|
||||
- missing context;
|
||||
- misframing risks;
|
||||
- recommended next step.
|
||||
|
||||
QPI does not solve the problem. It only controls routing and prevents framing mistakes.
|
||||
|
||||
## 3. Lens Orchestrator
|
||||
|
||||
Purpose: choose a small set of models/lenses for this run.
|
||||
|
||||
Default call budget:
|
||||
|
||||
- one primary model;
|
||||
- two or three support or contrast models at most;
|
||||
- one calibration lens when needed;
|
||||
- one reader translation layer when producing external-facing text.
|
||||
|
||||
M0-M1 only prepares the fields needed for this later choice. It does not implement a selector.
|
||||
|
||||
## 4. Deep Processing
|
||||
|
||||
Purpose: run the selected primary/depth model.
|
||||
|
||||
For startup, the only depth model is `intellectual_archaeology`. It should run only when the input has enough value, complexity, or reuse potential.
|
||||
|
||||
Depth processing must obey minimum sufficient depth. Continuing deeper is justified only when it changes judgment, path, validation, action boundary, or asset decision.
|
||||
|
||||
## 5. Synthesis & Calibration
|
||||
|
||||
Purpose: combine outputs and prevent a single model from over-claiming.
|
||||
|
||||
Expected output:
|
||||
|
||||
- main judgment;
|
||||
- supporting reasoning;
|
||||
- conflicts between model outputs;
|
||||
- evidence level;
|
||||
- action boundary;
|
||||
- what would change the conclusion.
|
||||
|
||||
## 6. Feedback & Asset Decision
|
||||
|
||||
Purpose: decide whether the run produced reusable learning.
|
||||
|
||||
Expected output:
|
||||
|
||||
- whether the output was useful;
|
||||
- whether the run should become a sample later;
|
||||
- whether a model card needs a future repair;
|
||||
- whether a new model need was exposed.
|
||||
|
||||
## 7. Reader Translation
|
||||
|
||||
Purpose: turn internal trace into a reader-facing explanation.
|
||||
|
||||
The internal output can contain model vocabulary and deep structure. The reader output must explain the actual issue, mechanism, example, boundary, and next way to think in language a non-model-maintainer can follow.
|
||||
|
|
@ -0,0 +1,64 @@
|
|||
# Decisions
|
||||
|
||||
status: draft_decision_log
|
||||
date: 2026-06-20
|
||||
|
||||
## D001: New Repository Boundary
|
||||
|
||||
Decision: `Cognitive-OS-Wantsong` is a new repository and not a continuation branch of `the-mindscape-of-bro-tsong`.
|
||||
|
||||
Reason: the old project is useful as a governance lab and seed archive, but its process gravity is not suitable for proving the runtime product question.
|
||||
|
||||
## D002: Runtime-First Startup Rule
|
||||
|
||||
Decision: the project follows `First prove cognitive processing. Only then govern the pieces that prove useful.`
|
||||
|
||||
Reason: the old failure mode was proving controlled model governance while postponing the real cognitive-processing loop.
|
||||
|
||||
## D003: M0-M1 Only
|
||||
|
||||
Decision: this startup creates only project boundary and model-management kernel files.
|
||||
|
||||
Reason: sample runs, prompts, examples, and review packets belong to later milestones.
|
||||
|
||||
## D004: No Lite Filenames
|
||||
|
||||
Decision: model filenames and model IDs do not use a `lite` suffix.
|
||||
|
||||
Reason: the new project is not a light branch of a completed old runtime. Minimality is expressed as `runtime_scope: minimal_v0`.
|
||||
|
||||
## D005: QPI Role
|
||||
|
||||
Decision: QPI is a `routing_model` for problem framing, scarcity diagnosis, and misframing detection.
|
||||
|
||||
Reason: QPI must not become the main governance object again.
|
||||
|
||||
## D006: Intellectual Archaeology Role
|
||||
|
||||
Decision: Intellectual Archaeology is the first `depth_model` and may be the primary model for complex high-value issues.
|
||||
|
||||
Reason: the new runtime must test real deep processing instead of mostly guarding the entrance to deep processing.
|
||||
|
||||
## D007: Local CCRA Lane
|
||||
|
||||
Decision: Local CCRA remains a milestone review lane only.
|
||||
|
||||
Reason: review quality remains useful, but default round factories and Web bundle production are outside the startup scope.
|
||||
|
||||
## D008: No Old Process Artifact Migration
|
||||
|
||||
Decision: old `reports/`, `ccra_review_bundle/`, `local_ccra_reviews/`, full regression, full selector calibration, lifecycle scan workflows, and Round Conductor are not migrated.
|
||||
|
||||
Reason: those artifacts represent the old project gravity and would recreate the failure mode.
|
||||
|
||||
## D009: Registry Before Selector
|
||||
|
||||
Decision: `models/model-registry.json` records model metadata and orchestration hooks, but no selector is implemented in M0-M1.
|
||||
|
||||
Reason: the system needs model identity and call boundaries before it needs automation.
|
||||
|
||||
## D010: Reader Translation As A Core Layer
|
||||
|
||||
Decision: reader translation is a first-class product layer, even though its prompt is not created in M0-M1.
|
||||
|
||||
Reason: internal model output is not automatically understandable or usable by frontend readers.
|
||||
|
|
@ -0,0 +1,62 @@
|
|||
# Local CCRA Milestone Protocol
|
||||
|
||||
status: draft_milestone_lane
|
||||
date: 2026-06-20
|
||||
|
||||
## Purpose
|
||||
|
||||
Local CCRA remains available as a milestone review lane.
|
||||
|
||||
It must not become a default round factory.
|
||||
|
||||
## Review Triggers
|
||||
|
||||
Use Local CCRA only at milestone boundaries, such as:
|
||||
|
||||
- project boundary ready;
|
||||
- first end-to-end runtime sample complete;
|
||||
- before adding the third or fourth model/lens;
|
||||
- before converting repeated runtime outputs into governed model assets;
|
||||
- before asking Web CCRA for formal acceptance.
|
||||
|
||||
## Non-Triggers
|
||||
|
||||
Do not start Local CCRA for:
|
||||
|
||||
- every prompt edit;
|
||||
- small model note changes;
|
||||
- routing wording changes;
|
||||
- registry field additions;
|
||||
- minor documentation cleanup.
|
||||
|
||||
## Review Package Shape
|
||||
|
||||
When a milestone review is explicitly started later, use a local-only directory such as:
|
||||
|
||||
```text
|
||||
local-ccra-reviews/milestone-XX/01/
|
||||
```
|
||||
|
||||
Expected files:
|
||||
|
||||
- `review-brief.md`;
|
||||
- `file-manifest.md`;
|
||||
- `prompt-to-send.md`;
|
||||
- `LOCAL_CCRA_REVIEW_REPORT.md`;
|
||||
- `returned-output.md`;
|
||||
- `owner-decision.md`.
|
||||
|
||||
Optional only when needed:
|
||||
|
||||
- `helper-outputs/`;
|
||||
- `next-review-requirements.md`.
|
||||
|
||||
## Authority
|
||||
|
||||
Local CCRA can identify findings and recommend repairs. It does not authorize repairs by itself.
|
||||
|
||||
Repairs require an owner decision. Web CCRA remains the strategic alignment and final-acceptance lane for major project direction.
|
||||
|
||||
## M0-M1 Boundary
|
||||
|
||||
M0-M1 defines this protocol only. It does not create a review directory or run a review.
|
||||
|
|
@ -0,0 +1,100 @@
|
|||
# Model Management V0
|
||||
|
||||
status: draft_callable_kernel
|
||||
date: 2026-06-20
|
||||
|
||||
## Purpose
|
||||
|
||||
Model management exists to make models callable in real cognitive processing. It is not the product itself.
|
||||
|
||||
M0-M1 defines enough structure to register and call the first two models:
|
||||
|
||||
- `qpi`;
|
||||
- `intellectual_archaeology`.
|
||||
|
||||
## Model Status
|
||||
|
||||
Allowed statuses:
|
||||
|
||||
- `seed`: source material or rough idea, not callable.
|
||||
- `draft`: model card exists but call boundary is incomplete.
|
||||
- `callable`: usable in a manual runtime with known limits.
|
||||
- `core_candidate`: repeatedly useful in real runs, pending milestone review.
|
||||
- `core_active`: accepted by owner after multiple useful runs and milestone review.
|
||||
- `needs_rework`: known boundary or quality issue blocks normal use.
|
||||
- `deprecated`: no longer recommended for new runs.
|
||||
- `archived`: retained only for history or reference.
|
||||
|
||||
M0-M1 may use only `draft` and `callable`.
|
||||
|
||||
## Model Levels
|
||||
|
||||
Allowed levels:
|
||||
|
||||
- `L0_source_material`: source article, discussion, report, or note.
|
||||
- `L1_candidate_model`: extracted candidate model, not yet callable.
|
||||
- `L2_callable_model`: callable manually with a known input/output contract.
|
||||
- `L3_core_model`: future state after repeated useful runs and milestone review.
|
||||
- `L4_long_term_core_model`: future state outside v0.1.
|
||||
|
||||
M0-M1 may use only `L1_candidate_model` and `L2_callable_model`.
|
||||
|
||||
## Required Model Card Fields
|
||||
|
||||
Each model card must state:
|
||||
|
||||
- `model_id`;
|
||||
- file path;
|
||||
- runtime scope;
|
||||
- governance level;
|
||||
- default role;
|
||||
- allowed roles;
|
||||
- one-sentence definition;
|
||||
- call conditions;
|
||||
- no-call conditions;
|
||||
- input types;
|
||||
- output contract;
|
||||
- depth or cost controls;
|
||||
- common misuses;
|
||||
- reader translation requirement;
|
||||
- source seed notes;
|
||||
- current limits.
|
||||
|
||||
## Registry Requirements
|
||||
|
||||
`models/model-registry.json` is the only structured registry in M0-M1.
|
||||
|
||||
The registry must support:
|
||||
|
||||
- locating the model file;
|
||||
- determining default role;
|
||||
- identifying whether a model can be primary, support, contrast, calibration, translation, or routing;
|
||||
- avoiding over-call by cost and no-call fields;
|
||||
- pairing QPI with later deep processing;
|
||||
- requiring reader translation when internal output is too model-heavy.
|
||||
|
||||
The registry is not a full schema system.
|
||||
|
||||
## Upgrade Rule
|
||||
|
||||
A model cannot be upgraded because JSON parses, docs exist, or a selector could call it.
|
||||
|
||||
Future upgrades require:
|
||||
|
||||
- real run evidence;
|
||||
- owner review;
|
||||
- quality review at a milestone;
|
||||
- clear usefulness beyond one sample;
|
||||
- explicit decision entry.
|
||||
|
||||
## Stop Conditions
|
||||
|
||||
Stop model-management expansion if work starts to require:
|
||||
|
||||
- complete evidence matrices before the first real runtime sample;
|
||||
- a full regression suite;
|
||||
- full selector calibration;
|
||||
- lifecycle promotion machinery;
|
||||
- proof that every boundary case is covered.
|
||||
|
||||
Those belong later, after the runtime proves value.
|
||||
|
|
@ -0,0 +1,84 @@
|
|||
# Model Orchestration V0
|
||||
|
||||
status: draft_orchestration_boundary
|
||||
date: 2026-06-20
|
||||
|
||||
## Purpose
|
||||
|
||||
Orchestration decides which small set of models should participate in a cognitive-processing run.
|
||||
|
||||
M0-M1 only defines the decision fields and call limits. It does not implement a selector.
|
||||
|
||||
## Roles
|
||||
|
||||
- `routing_model`: classifies input and controls next-step routing.
|
||||
- `depth_model`: performs vertical deep processing.
|
||||
- `primary_model`: main explanatory model for a run.
|
||||
- `support_model`: fills a known blind spot of the primary model.
|
||||
- `contrast_model`: challenges or reframes the primary model.
|
||||
- `calibration_model`: checks evidence, action boundary, or overclaim risk.
|
||||
- `translation_model`: rewrites internal output for reader use.
|
||||
- `synthesis_model`: integrates outputs into a coherent judgment.
|
||||
|
||||
## Startup Defaults
|
||||
|
||||
`qpi`:
|
||||
|
||||
- default role: `routing_model`;
|
||||
- should run before deep processing when problem framing is unclear;
|
||||
- should stop at routing and misframing diagnosis.
|
||||
|
||||
`intellectual_archaeology`:
|
||||
|
||||
- default role: `depth_model`;
|
||||
- can become `primary_model` for complex, high-value, reusable, or repeatedly failing issues;
|
||||
- should run after intake/QPI justifies deeper work.
|
||||
|
||||
## Single-Run Call Budget
|
||||
|
||||
A normal run may include at most:
|
||||
|
||||
- one primary model;
|
||||
- two or three support or contrast models;
|
||||
- one calibration lens;
|
||||
- one reader translation layer.
|
||||
|
||||
Do not call every related model. A model must add explanatory value, reduce a blind spot, or change the action boundary.
|
||||
|
||||
## Main Model Selection Signals
|
||||
|
||||
Primary model choice should consider:
|
||||
|
||||
- problem type match;
|
||||
- explanatory gain;
|
||||
- intended output;
|
||||
- model maturity;
|
||||
- processing cost.
|
||||
|
||||
Do not use simple keyword matching as the final selection method.
|
||||
|
||||
## Support Model Entry Conditions
|
||||
|
||||
A support model may enter only when:
|
||||
|
||||
- the primary model has a known blind spot;
|
||||
- the primary model may over-explain;
|
||||
- the issue needs comparison, contrast, or calibration.
|
||||
|
||||
## Guardrails
|
||||
|
||||
- QPI is not the product output.
|
||||
- Intellectual Archaeology is not default for light tasks.
|
||||
- No full selector in M0-M1.
|
||||
- No flat scoring across a large model universe.
|
||||
- No expansion beyond the two startup models without owner instruction.
|
||||
|
||||
## Future 100-Model Direction
|
||||
|
||||
If the project later grows toward many models, orchestration should use a layered path:
|
||||
|
||||
```text
|
||||
input -> domain/problem family -> 5-8 candidates -> 1 primary -> 2-3 support/contrast -> calibration -> synthesis -> translation
|
||||
```
|
||||
|
||||
This future direction is only a design hook. It is not part of v0.1 implementation.
|
||||
|
|
@ -0,0 +1,76 @@
|
|||
# Project Brief
|
||||
|
||||
status: draft_runtime_boundary
|
||||
date: 2026-06-20
|
||||
|
||||
## One-Sentence Definition
|
||||
|
||||
`Cognitive-OS-Wantsong` is a lightweight cognitive-processing runtime that uses Wantsong's cognitive models to process complex inputs into internal analysis and reader-facing explanations.
|
||||
|
||||
## Restart Basis
|
||||
|
||||
The old project proved useful file-first model-governance mechanisms, but its operating gravity drifted toward review evidence, selector calibration, regression cases, and lifecycle caution.
|
||||
|
||||
This project starts from the opposite order:
|
||||
|
||||
```text
|
||||
run real cognitive workflow -> inspect output value -> stabilize useful model pieces
|
||||
```
|
||||
|
||||
M0-M1 therefore creates only the boundary and model-management kernel required before any runtime sample.
|
||||
|
||||
## Product Layers
|
||||
|
||||
The project has three layers and one review lane:
|
||||
|
||||
1. Model management layer: register, describe, call, combine, retire, and repair model assets.
|
||||
2. Cognitive-processing runtime layer: intake, QPI, lens orchestration, deep processing, synthesis, calibration, and feedback.
|
||||
3. Reader translation layer: turn internal model output into understandable reader-facing expression.
|
||||
4. Milestone quality lane: Local CCRA reviews milestone outputs, not every small edit.
|
||||
|
||||
## M0 Acceptance
|
||||
|
||||
M0 is acceptable when:
|
||||
|
||||
- the repo has an independent git boundary and remote;
|
||||
- the old project is documented only as reference and seed archive;
|
||||
- forbidden old process artifacts are not present;
|
||||
- v0.1 non-goals are explicit.
|
||||
|
||||
## M1 Acceptance
|
||||
|
||||
M1 is acceptable when:
|
||||
|
||||
- QPI and Intellectual Archaeology have callable model cards;
|
||||
- `models/model-registry.json` supports future primary/support selection;
|
||||
- model statuses and levels are defined without creating a full lifecycle system;
|
||||
- no full selector, full schema validator, sample run, or regression suite exists.
|
||||
|
||||
## Non-Goals For v0.1 Startup
|
||||
|
||||
- full model library;
|
||||
- 10-model expansion;
|
||||
- complete schema validator;
|
||||
- database;
|
||||
- backend service;
|
||||
- frontend UI;
|
||||
- vector database;
|
||||
- full RAG;
|
||||
- full regression suite;
|
||||
- lifecycle promotion;
|
||||
- before/after selector diff;
|
||||
- Web review bundle by default;
|
||||
- old report migration;
|
||||
- old review-bundle migration;
|
||||
- old Local CCRA history migration;
|
||||
- Round Conductor.
|
||||
|
||||
## Failure Signals
|
||||
|
||||
M0-M1 is drifting if:
|
||||
|
||||
- QPI becomes the main governance object again;
|
||||
- review artifacts outgrow runtime artifacts before the first sample;
|
||||
- Codex creates `round-*`, `ccra_review_bundle/`, or full regression material;
|
||||
- model management starts requiring perfect evidence matrices before any runtime use;
|
||||
- reader translation is ignored as a product layer.
|
||||
|
|
@ -0,0 +1,52 @@
|
|||
# Reader Translation Layer V0
|
||||
|
||||
status: draft_translation_boundary
|
||||
date: 2026-06-20
|
||||
|
||||
## Purpose
|
||||
|
||||
Internal cognitive processing can use Wantsong's model vocabulary, formulas, metaphors, layered reasoning, and mechanism chains.
|
||||
|
||||
Reader-facing output cannot simply expose that internal trace. It must translate the result into language a reader can use.
|
||||
|
||||
## Output Modes
|
||||
|
||||
M0-M1 recognizes these modes:
|
||||
|
||||
- `R0_internal_trace`: internal analysis record for owner inspection.
|
||||
- `R1_owner_brief`: compact owner-facing quality summary.
|
||||
- `R2_reader_explanation`: explanation for a normal reader.
|
||||
- `R3_publishable_draft`: future writing-workbench draft.
|
||||
- `R4_product_response`: future product answer.
|
||||
|
||||
v0.1 targets only `R0_internal_trace` and `R2_reader_explanation`.
|
||||
|
||||
## Translation Operations
|
||||
|
||||
Reader translation performs four operations:
|
||||
|
||||
1. Terminology translation: replace model jargon with ordinary language.
|
||||
2. Structure translation: reorder the reasoning so a reader can follow it.
|
||||
3. Example translation: use concrete examples to carry abstract mechanisms.
|
||||
4. Action translation: turn insight into "how to see this / what to consider next".
|
||||
|
||||
## What To Preserve
|
||||
|
||||
- core insight;
|
||||
- mechanism;
|
||||
- boundaries;
|
||||
- Wantsong-style distinction and depth;
|
||||
- practical next way to think.
|
||||
|
||||
## What To Remove Or Compress
|
||||
|
||||
- full model trace;
|
||||
- unnecessary formulas;
|
||||
- seven-layer expansion when only three layers matter;
|
||||
- governance vocabulary;
|
||||
- generic disclaimers;
|
||||
- marketing exaggeration.
|
||||
|
||||
## Boundary
|
||||
|
||||
This layer is defined now because it changes model-card requirements. The actual translation prompt is not created in M0-M1.
|
||||
|
|
@ -0,0 +1,110 @@
|
|||
# Intellectual Archaeology
|
||||
|
||||
model_id: intellectual_archaeology
|
||||
file: models/intellectual-archaeology.md
|
||||
runtime_scope: minimal_v0
|
||||
governance_level: draft_callable
|
||||
status: callable
|
||||
model_level: L2_callable_model
|
||||
default_role: depth_model
|
||||
allowed_roles: depth_model, primary_model
|
||||
reader_translation_required: true
|
||||
|
||||
## One-Sentence Definition
|
||||
|
||||
Intellectual Archaeology is a depth-processing model that drills from surface application down through deeper structural layers to expose hidden assumptions, core mechanisms, and action-relevant boundaries.
|
||||
|
||||
## Runtime Role
|
||||
|
||||
Intellectual Archaeology is the first deep-processing engine in this project.
|
||||
|
||||
It is not a front router, not a summary format, and not a default response style. It should be called only when Intake and QPI indicate that deeper modeling is worth the cost.
|
||||
|
||||
## Core Question
|
||||
|
||||
What deeper structural assumptions make this issue, model, or judgment work, and at what depth does further excavation stop changing the decision?
|
||||
|
||||
## Layer Framework
|
||||
|
||||
The model uses seven possible layers:
|
||||
|
||||
1. `application`: surface task, tool, behavior, or symptom.
|
||||
2. `domain`: domain topology, evaluation frame, actors, and constraints.
|
||||
3. `process`: time evolution, feedback, lifecycle, and path dependence.
|
||||
4. `purpose`: value target, tradeoff, stakeholder balance, and QPI alignment.
|
||||
5. `core_mechanism`: generative mechanism, system dynamics, and causal structure.
|
||||
6. `human_capability`: cognitive, biological, organizational, or skill limits.
|
||||
7. `philosophical_bedrock`: basic assumptions about reality, meaning, order, and agency.
|
||||
|
||||
## Minimum Sufficient Depth
|
||||
|
||||
Do not automatically drill to the deepest layer.
|
||||
|
||||
Continue deeper only if it changes at least one of:
|
||||
|
||||
- judgment;
|
||||
- solution path;
|
||||
- evidence requirement;
|
||||
- risk weighting;
|
||||
- action boundary;
|
||||
- reusable model asset decision.
|
||||
|
||||
## Call When
|
||||
|
||||
- QPI classifies the input as a medium/heavy `problem` or `issue`.
|
||||
- A surface explanation keeps failing.
|
||||
- The issue has high reuse value.
|
||||
- The owner wants to extract a model from source material.
|
||||
- The problem needs hidden assumptions made explicit.
|
||||
- A model or product logic needs depth inspection.
|
||||
|
||||
## Do Not Call When
|
||||
|
||||
- The input is a fact lookup.
|
||||
- The user needs a short execution answer.
|
||||
- There is not enough source material to distinguish mechanism from speculation.
|
||||
- Deeper analysis will not change judgment or action.
|
||||
- The user explicitly asks not to enter depth processing.
|
||||
|
||||
## Input Types
|
||||
|
||||
- complex issue;
|
||||
- recurring failure;
|
||||
- cognitive model draft;
|
||||
- source article or report for model extraction;
|
||||
- strategic, product, or organizational reasoning problem;
|
||||
- hidden-assumption audit.
|
||||
|
||||
## Output Contract
|
||||
|
||||
Intellectual Archaeology output must include:
|
||||
|
||||
- `should_call`;
|
||||
- `entry_reason`;
|
||||
- `recommended_max_depth`;
|
||||
- `layers_to_analyze`;
|
||||
- `analysis_by_layer`;
|
||||
- `stop_reason`;
|
||||
- `no_deeper_reason`;
|
||||
- `assumptions_by_layer`;
|
||||
- `core_mechanism_summary`;
|
||||
- `validation_needed`;
|
||||
- `action_implication`;
|
||||
- `reader_translation_notes`.
|
||||
|
||||
## Common Misuses
|
||||
|
||||
- Using the model as a long summary.
|
||||
- Forcing every issue to the philosophical layer.
|
||||
- Producing abstract depth without changing action.
|
||||
- Ignoring QPI and value-assessment controls.
|
||||
- Treating internal coherence as real-world validity.
|
||||
- Forgetting reader translation.
|
||||
|
||||
## Source Seed Notes
|
||||
|
||||
Seeded from the old Intellectual Archaeology model/card and the seven-layer example report, rewritten for this runtime. Old regression suites, selector gates, review reports, and Local CCRA histories are not migrated.
|
||||
|
||||
## Current Limits
|
||||
|
||||
This model is callable for manual runtime use, but its depth stops and layer quality require real-run calibration before any upgrade.
|
||||
|
|
@ -0,0 +1,127 @@
|
|||
{
|
||||
"registry_id": "cognitive_os_wantsong_model_registry",
|
||||
"version": "0.1.0",
|
||||
"date": "2026-06-20",
|
||||
"runtime_scope": "minimal_v0",
|
||||
"status": "draft_callable_registry",
|
||||
"notes": [
|
||||
"M0-M1 registry only. This is not a full selector, schema system, or lifecycle engine.",
|
||||
"No model filenames or model IDs use lite suffixes.",
|
||||
"Old review bundles, reports, Local CCRA histories, full regression, and selector calibration are not migrated."
|
||||
],
|
||||
"allowed_roles": [
|
||||
"routing_model",
|
||||
"depth_model",
|
||||
"primary_model",
|
||||
"support_model",
|
||||
"contrast_model",
|
||||
"calibration_model",
|
||||
"translation_model",
|
||||
"synthesis_model"
|
||||
],
|
||||
"single_run_call_budget": {
|
||||
"primary_model_max": 1,
|
||||
"support_or_contrast_model_max": 3,
|
||||
"calibration_model_max": 1,
|
||||
"translation_model_max": 1
|
||||
},
|
||||
"models": [
|
||||
{
|
||||
"model_id": "qpi",
|
||||
"display_name": "QPI",
|
||||
"file": "models/qpi.md",
|
||||
"model_family": "problem_framing",
|
||||
"status": "callable",
|
||||
"model_level": "L2_callable_model",
|
||||
"runtime_scope": "minimal_v0",
|
||||
"governance_level": "draft_callable",
|
||||
"default_role": "routing_model",
|
||||
"allowed_roles": [
|
||||
"routing_model",
|
||||
"calibration_model"
|
||||
],
|
||||
"pipeline_position": "pre_analysis",
|
||||
"can_be_primary": false,
|
||||
"can_be_support": true,
|
||||
"can_be_contrast": false,
|
||||
"can_be_calibration": true,
|
||||
"reader_translation_required": true,
|
||||
"best_for": [
|
||||
"problem_definition",
|
||||
"dominant_scarcity_detection",
|
||||
"misframing_risk",
|
||||
"routing_before_depth"
|
||||
],
|
||||
"avoid_for": [
|
||||
"fact_lookup",
|
||||
"direct_execution",
|
||||
"copyediting",
|
||||
"final_answer_generation"
|
||||
],
|
||||
"cost_level": "low",
|
||||
"call_before": [
|
||||
"intellectual_archaeology"
|
||||
],
|
||||
"call_after": [],
|
||||
"pairs_well_with": [
|
||||
"intellectual_archaeology"
|
||||
],
|
||||
"conflicts_with": [],
|
||||
"source_seed": [
|
||||
"old_project_cards_qpi",
|
||||
"old_project_models_qpi",
|
||||
"wantsong_cognitive_os_source"
|
||||
]
|
||||
},
|
||||
{
|
||||
"model_id": "intellectual_archaeology",
|
||||
"display_name": "Intellectual Archaeology",
|
||||
"file": "models/intellectual-archaeology.md",
|
||||
"model_family": "deep_modeling",
|
||||
"status": "callable",
|
||||
"model_level": "L2_callable_model",
|
||||
"runtime_scope": "minimal_v0",
|
||||
"governance_level": "draft_callable",
|
||||
"default_role": "depth_model",
|
||||
"allowed_roles": [
|
||||
"depth_model",
|
||||
"primary_model"
|
||||
],
|
||||
"pipeline_position": "deep_analysis",
|
||||
"can_be_primary": true,
|
||||
"can_be_support": false,
|
||||
"can_be_contrast": false,
|
||||
"can_be_calibration": false,
|
||||
"reader_translation_required": true,
|
||||
"best_for": [
|
||||
"deep_structure",
|
||||
"hidden_assumptions",
|
||||
"mechanism_excavation",
|
||||
"reusable_model_extraction",
|
||||
"recurring_failure_analysis"
|
||||
],
|
||||
"avoid_for": [
|
||||
"fact_lookup",
|
||||
"light_rewrite",
|
||||
"low_stakes_execution",
|
||||
"insufficient_source_material"
|
||||
],
|
||||
"cost_level": "high",
|
||||
"call_before": [],
|
||||
"call_after": [
|
||||
"qpi"
|
||||
],
|
||||
"pairs_well_with": [
|
||||
"qpi"
|
||||
],
|
||||
"conflicts_with": [
|
||||
"fast_execution_flow"
|
||||
],
|
||||
"source_seed": [
|
||||
"old_project_cards_intellectual_archaeology",
|
||||
"old_project_models_intellectual_archaeology",
|
||||
"seven_layer_ia_example_report"
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
|
|
@ -0,0 +1,133 @@
|
|||
# QPI
|
||||
|
||||
model_id: qpi
|
||||
file: models/qpi.md
|
||||
runtime_scope: minimal_v0
|
||||
governance_level: draft_callable
|
||||
status: callable
|
||||
model_level: L2_callable_model
|
||||
default_role: routing_model
|
||||
allowed_roles: routing_model, calibration_model
|
||||
reader_translation_required: true
|
||||
|
||||
## One-Sentence Definition
|
||||
|
||||
QPI classifies how a cognitive subject frames an expectation-reality gap as `question`, `problem`, `issue`, `mixed`, or `no_call`, then identifies missing context, dominant scarcity, dynamic stage, and misframing risk.
|
||||
|
||||
## Runtime Role
|
||||
|
||||
QPI is a front-routing and misframing-diagnostic model.
|
||||
|
||||
It should run before deep processing when problem framing is unclear. It should not replace deep processing, synthesis, or final answer generation.
|
||||
|
||||
## Core Question
|
||||
|
||||
Who, in what scenario, frames which expectation-reality gap as what kind of problem, and what context is missing before the framing can be trusted?
|
||||
|
||||
## Core Mechanism
|
||||
|
||||
QPI checks:
|
||||
|
||||
- problem owner;
|
||||
- subject position;
|
||||
- scenario context;
|
||||
- responsibility scope;
|
||||
- problem source;
|
||||
- time scale;
|
||||
- expectation-reality gap;
|
||||
- three scarcity types.
|
||||
|
||||
Scarcity mapping:
|
||||
|
||||
- `question`: data or fact scarcity;
|
||||
- `problem`: path, method, or resource scarcity;
|
||||
- `issue`: consensus, certainty, order, or dynamic-balance scarcity;
|
||||
- `mixed`: multiple scarcity types in the same subject/scenario frame;
|
||||
- `no_call`: input does not need QPI.
|
||||
|
||||
QPI must distinguish same-frame mixed scarcity from cross-viewpoint divergence.
|
||||
|
||||
## Call When
|
||||
|
||||
- The user asks what the real problem is.
|
||||
- The input mixes facts, path constraints, interests, and system structure.
|
||||
- The problem owner or responsibility boundary is unclear.
|
||||
- The user is rushing to solve before defining the issue.
|
||||
- There is risk of violent reduction, malicious inflation, or means-end mismatch.
|
||||
- A later model needs routing support.
|
||||
|
||||
## Do Not Call When
|
||||
|
||||
- The user only asks for a clear fact lookup.
|
||||
- The user gives a direct execution task.
|
||||
- The user asks for copyediting or format conversion.
|
||||
- The problem has already been framed and only needs the next execution step.
|
||||
- The user explicitly asks not to analyze, unless they narrowly request QPI-only classification.
|
||||
|
||||
## Input Types
|
||||
|
||||
- ambiguous problem statement;
|
||||
- business or product issue description;
|
||||
- organizational conflict narrative;
|
||||
- unclear requirement or failure report;
|
||||
- owner reflection that needs problem-definition help.
|
||||
|
||||
## Output Contract
|
||||
|
||||
QPI output must include:
|
||||
|
||||
- `classification_scope`: `subject_contextual | multi_perspective | insufficient_context | no_call`;
|
||||
- `classification`: `question | problem | issue | mixed | no_call`;
|
||||
- `classification_confidence`: `high | medium | low`;
|
||||
- `is_provisional`;
|
||||
- `problem_owner`;
|
||||
- `subject_position`;
|
||||
- `scenario_context`;
|
||||
- `responsibility_scope`;
|
||||
- `problem_source`;
|
||||
- `time_scale`;
|
||||
- `expectation_reality_gap`;
|
||||
- `context_sufficiency`;
|
||||
- `missing_context`;
|
||||
- `scarcity_profile`;
|
||||
- `dominant_scarcity`;
|
||||
- `classification_reason`;
|
||||
- `classification_by_viewpoint`;
|
||||
- `dynamic_stage`;
|
||||
- `possible_trajectory`;
|
||||
- `success_criteria_stability`;
|
||||
- `hard_feedback_availability`;
|
||||
- `governance_load`;
|
||||
- `evidence_gap`;
|
||||
- `misclassification_risk`;
|
||||
- `recommended_clarifying_questions`;
|
||||
- `recommended_next_step`;
|
||||
- `next_model_candidates`.
|
||||
|
||||
## Depth Control
|
||||
|
||||
Stop at QPI when:
|
||||
|
||||
- the input is a fact lookup;
|
||||
- classification evidence is too thin;
|
||||
- the user only needs a narrow problem-type judgment;
|
||||
- negative triggers suppress analysis.
|
||||
|
||||
Recommend `intellectual_archaeology` only when the issue is high-value, recurring, structurally complex, or likely to benefit from depth processing.
|
||||
|
||||
## Common Misuses
|
||||
|
||||
- Treating QPI as a full answer.
|
||||
- Turning QPI into the main governance battlefield.
|
||||
- Classifying by keywords without owner/scenario context.
|
||||
- Calling every complex-looking input an `issue`.
|
||||
- Collapsing cross-viewpoint divergence into same-frame `mixed`.
|
||||
- Using QPI to delay a direct fact lookup or simple execution task.
|
||||
|
||||
## Source Seed Notes
|
||||
|
||||
Seeded from the old QPI model/card and Wantsong cognitive-system source material, rewritten for this runtime. Old regression suites, selector calibration, and review artifacts are not migrated.
|
||||
|
||||
## Current Limits
|
||||
|
||||
This model is callable for manual runtime use, but it is not a reviewed core model. It needs real-run evidence before any upgrade.
|
||||
Loading…
Reference in New Issue