weave-asklisted

# Weave Ask Ask a question across multiple AI models (Claude, Antigravity, GPT) in parallel, then synthesize the best answer from all responses. This is a **project-read-only** command — no files in your repository are written, edited, or deleted. Session artifacts (model outputs, prompts, synthesis results) are persisted to `$AI_AIP_ROOT` for post-session inspection; this directory is outside your repository. The question comes from `$ARGUMENTS`. If no arguments are provided, ask the user what they want to know. --- ## Phase 1: Gather Context **Goal**: Understand the project and prepare the question. 1. **Read CLAUDE.md / AGENTS.md** if present — project conventions inform better answers. 2. **Determine trunk branch** (for questions about branch changes): ```bash git remote show origin | grep 'HEAD branch' ``` Fall back to `main`, then `master`, if detection fails. 3. **Capture the question**: Use `$ARGUMENTS` as the user's question. If `$ARGUMENTS` is empty, ask the user what question they want answered. --- ## Phase 1b: Build Context Packet After Phase 1 context gathering (reading CLAUDE.md, exploring files, capturing the task), assemble a structured context bundle that will be included verbatim in ALL model prompts. This ensures every model works from the same information. Write to `$SESSION_DIR/context-packet.md` *(the actual file write happens after Session Directory Initialization in Phase 2 creates `$SESSION_DIR`)*: 1. **Conventions summary**