v0.42.0

v0.42.0: leaner tool output and configurable backups

This release focuses on the cost of every tool call — how much context AFT's navigation and search tools spend to answer a question — and adds configurable file backups behind undo. The output changes were measured against an external head-to-head benchmark suite and cut AFT's per-task tool-context cost substantially at unchanged answer quality.

Leaner navigation and search output

The navigation and search tools were dumping more than the agent needed: a whole class body when only a menu of its methods was wanted, every standard-library call in a call tree, the same callee repeated once per call site. This release trims each of these to what's actually useful, with no loss of information.

• aft_zoom on a large container returns a member menu, not the whole body. Zooming a class, struct, impl, trait, or enum larger than ~150 lines now returns its members listed with their signatures and line ranges — the same shape aft_outline gives a file — instead of the entire body. Zooming a specific method still returns its full body; a small container is still returned whole. This stops one zoom of a large class from spending tens of thousands of characters the agent then bypasses to zoom the method it actually wanted.
• aft_search expands only the top match, within a budget. The top result is shown as full symbol source (so it can be edited without a re-read); ranks 2-3 are short previews; the rest are headers only. If the top match is itself a large symbol, it is rendered within a budget — a member menu for a big container, a head slice for a big function — rather than dumped whole.
• aft_callgraph collapses standard-library noise. In call_tree, unresolved external/stdlib calls (len, Some, clone, …) are folded into one summary line per caller instead of one line each. These made up over half of call-graph output and can't be navigated anyway. Resolved, project-internal edges are unchanged. Pass includeUnresolved=true to see every edge individually.
• aft_zoom call lists are deduplicated. calls_out / called_by now list each callee once with a count, instead of repeating a line per call site.
• Ambiguous name zooms return candidate signatures to choose from, instead of an error.
• Generated documentation trees are down-ranked in search. Committed jazzy/javadoc/sphinx output (.html/.css/.json artifacts) no longer crowds real source out of aft_search's top results. grep stays exhaustive and unchanged; hand-written docs are unaffected.
• aft_search invites natural-language questions for conceptual queries (its semantic lane is tuned for intent), and hides test files by default.

Configurable backups behind undo

aft_safety's undo is backed by per-file snapshots on disk. This release makes that configurable and removes write amplification from the edit hot path:

• New settings: backup.enabled (default true), backup.max_depth (default 20), and backup.max_file_size — control whether backups are kept, how deep the per-file history goes, and a size ceiling above which a file isn't snapshotted.
• Faster edits. Each edit now appends a single backup file instead of rewriting the entire backup stack, so backup cost no longer grows with history depth.
• Rollback safety is preserved. Internal transactional rollback for failed multi-file refactors and renames stays active regardless of the backup.enabled setting.

Search ranking

Semantic search adds ranking priors that lift exact-name definitions and "type + concept" matches, improving retrieval on identifier and concept queries without changing the index format or requiring a re-index.

Fixes

• Editing Rust code containing &raw (a variable named raw passed by reference, e.g. handle(&raw)) no longer fails validation and silently rolls back. Bumped tree-sitter-rust and several other grammars to current releases.
• Editing files whose paths contain [brackets] or {braces} — e.g. Next.js dynamic routes like app/[id]/page.tsx — now resolves the literal path first instead of treating it as a glob pattern. Thanks to @tobwen.
• Dependency bumps: zod, @opencode-ai/*, the Pi SDK, and @clack/prompts.

Under the hood

• Lower peak memory and CPU during indexing: cold semantic builds and the Tier-2 code-health scan are serialized so they don't pile onto the same cores at once.