Automated README summary
Automatically summarized from the README on 16 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Astra-Ares is an experimental reference implementation that adapts GPT-6's reasoning effort while a Codex task runs, aiming to reduce token usage by matching reasoning depth to the next step. It is for developers integrating adaptive reasoning into agent systems.
How it uses Jev
Jev reads bounded task context (task, progress, recent tool results) and chooses the next reasoning effort and how many generations it lasts. Codex applies the choice natively; the result is used to adjust the model's effort without invalidating the prompt prefix.
Primitives:choice
Technique worth stealing
Use native configuration_update to change reasoning effort mid-conversation while preserving the prompt prefix for cache reuse.
Try it
git clone, npm ci, npm run setup, npm link, ares configure, then astra-ares.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.65
- Shows a System One patternnot found in the excerpt0.20
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.67
- Top-10 learning shortlist signalnot found in the excerpt0.25
- Is a replica of the modelnot found in the excerpt0.19
- Solves a common problem (0–2)score on a 0–2 scale0.99 / 2
- About JevFound in material0.93
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 16 Oct 2026.