7-e1even
Featured
learn-agent
A collection of notes on building coding agents, derived from the production development of the desktop agent Reina, with each mechanism simplified into a zero-dependency, single-file Node.js demo.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It introduces a systematic, quality-per-token routing strategy for GPT-5.6 models, with explicit model-aware sends, independent subagent classification, and no fallback to older models.
Who it is for
- Developers using Codex CLI or GPT Work
- Teams automating complex code generation and debugging workflows
- Users of GPT Codex who want fine-grained model selection for subtasks
- Engineers optimizing AI-assisted development costs and throughput
Use cases
- Routing a mechanical task to Luna Low and a subtle cross‑module fix to Terra High
- Delegating a security‑critical subtask to Sol even when the parent task uses Luna
- Explicitly verifying that the running model and effort match the selected route before proceeding
- Forking a Codex task with explicit model and thinking parameters to guarantee the intended model is used
Strengths
- Each subtask is independently classified and receives explicit model and reasoning_effort values
- Never falls back to GPT-5.5 or other non‑5.6 models; routes only among Luna, Terra, or Sol
- Uses the closest native Codex API equivalent when in‑place hot swap is unavailable and reports the route honestly
- Ultra reasoning is never selected automatically and hidden max is never used
Considerations
- No in‑place hot swap for a running Codex host task; requires a visible fork
- Ultra reasoning is only activated on explicit user request, not automatically
- Installation requires manual cloning and running a script, with no package manager integration
README quick start
GPT5.6-SOLTELU Model Inverter
Quality-per-token model routing for GPT Codex, GPT Work, and Codex CLI.
English
What It Does
GPT5.6-SOLTELU Model Inverter selects the most appropriate GPT-5.6 model and reasoning effort for the main task and every delegated subtask:
| Work type | Default route |
|---|---|
| Clear, mechanical, inexpensive to retry | Luna Low or Medium |
| Normal implementation and bounded debugging | Terra Medium |
| Subtle cross-module implementation | Terra High or Extra High |
| Architecture, conflicting evidence, security, data, or production risk | Sol High or Extra High |
The objective is not minimum token use. It is the best balance between answer quality, reasoning cost, handoff cost, verification, and avoided rework.
Routing is limited to gpt-5.6-luna, gpt-5.6-terra, and gpt-5.6-sol. It never falls back to GPT-5.5 or another non-5.6 model; it selects another appropriate GPT-5.6 profile or reports the unavailable gate.
Codex-First Routing
Codex is the primary workflow. For nontrivial work, the skill stays in place only when the current model and effort are positively verified to exactly match the selected route. Unknown settings count as a mismatch: when native controls are available, it must create one visible same-directory Codex fork, send the active request with explicit model and thinking, and open that task so the user continues working directly in the selected model.
The current Codex API does not expose an in-place hot swap for a running host task. GPT5.6-SOLTELU Model Inverter uses the closest native equivalent and reports the route honestly. A profile label alone never counts as a model switch; the explicit model-aware send must succeed first.
Subagent Optimization
Every delegated subtask is classified independently. A Sol parent does not force Sol children, and a Luna parent does not prevent a security-critical child from using Sol. Each spawn receives explicit model and reasoning_effort values.
Ultra is never selected automatically. It is available only when the user explicitly requests Ultra in the current task. Hidden max is never used.
Install
git clone https://github.com/AlexAI-MCP/GPT5.6-SOLTELU-Model-Inverter.git
cd GPT5.6-SOLTELU-Model-Inverter
./scripts/install.sh
Use a custom home or preview the destinati
Description
Quality-per-token GPT-5.6 Sol, Terra, and Luna model router for Codex, Work, CLI, and subagents.
Related repositories
Similar projects matched by category, topics, and programming language.
powerycy
Featured
goutoujunshi
An AI relationship coach that provides emotional support, relationship science, and actionable strategies through a multidisciplinary knowledge base.
makecindy
Featured
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.