mirror of
https://github.com/davidkaya/aryx.git
synced 2026-08-08 20:58:45 +02:00
feat: add phase 3 prompt customization backend
- parse prompt model and argument-hint metadata and persist model on prompt invocations - expand markdown-linked file context in scanned prompt and instruction bodies - discover .claude/rules instructions and support Claude-style paths metadata - discover customization roots up to the nearest parent repository and watch them for changes - apply per-turn prompt model overrides before sidecar execution Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
@@ -57,7 +57,7 @@ Aryx is a desktop app that turns GitHub Copilot into a full workspace. Connect r
|
||||
| Mid-turn steering | Send follow-up messages while an agent is running — input is injected immediately |
|
||||
| Plan review & questions | Agents propose plans and ask clarifying questions before acting |
|
||||
| Run timeline | Structured history of tool calls, delegations, hooks, and context usage |
|
||||
| Copilot customization | Auto-discovers repo instructions (`copilot-instructions.md`, `AGENTS.md`, `CLAUDE.md`, `.instructions.md`), agent profiles, and prompt files from your repo, then auto-rescans when those files change |
|
||||
| Copilot customization | Auto-discovers repo instructions (`copilot-instructions.md`, `AGENTS.md`, `CLAUDE.md`, `.instructions.md`, `.claude/rules`), agent profiles, and prompt files across nested repo roots, expands Markdown-linked context, exposes prompt metadata (`tools`, `model`, `argument-hint`), then auto-rescans when those files change |
|
||||
| Model & effort tuning | Choose models, adjust reasoning effort, and set interaction modes per session |
|
||||
|
||||
### Developer tooling
|
||||
|
||||
Reference in New Issue
Block a user