@kmugalkhod/lightcode 0.10.0 → 0.12.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/README.md +6 -3
  2. package/cli.js +6001 -2962
  3. package/package.json +13 -1
  4. package/server.js +10117 -5416
package/README.md CHANGED
@@ -27,9 +27,10 @@ bun run cli:dev # starts the TUI; it boots the server automatically
27
27
  ```
28
28
 
29
29
  Lightcode is aware of the directory you launch it in: each turn it reads the
30
- project's shape (top-level files, git branch/status) and any `AGENTS.md` /
31
- `CLAUDE.md` / `README.md`, so "review my code" or "explain this" inspects your
32
- actual files instead of asking you to paste them.
30
+ project's shape (top-level files and git branch/status), uses root `AGENTS.md`
31
+ instructions with `CLAUDE.md` as a fallback, and loads nested instructions only
32
+ when related paths are accessed. `README.md` remains ordinary project context,
33
+ not privileged instructions.
33
34
 
34
35
  On first run Lightcode walks you through provider setup (Anthropic,
35
36
  OpenRouter, OpenCode Zen, or any OpenAI-compatible endpoint) and stores the
@@ -61,6 +62,8 @@ variables. Notable keys:
61
62
  | `context.compactAtFraction` | Context compaction threshold (default 0.8) |
62
63
  | `context.pruneAtFraction` | Tool-output pruning threshold (default 0.6) |
63
64
  | `context.contextWindowOverride` | Override the model context window |
65
+ | `webSearch.backend` | `auto`, `provider`, `brave`, `tavily`, or `disabled` |
66
+ | `webSearch.maxResults`, `webSearch.maxUsesPerTurn` | Bound search results and per-turn search usage |
64
67
  | `maxRetries` | Provider-call retries for transient errors (default 5) |
65
68
  | `autoContinue.stallTimeoutSeconds` | Abort+retry a byte-silent stream (default 300; raise for very slow reasoning models) |
66
69
  | `autoContinue.maxErrorRetries` | Auto-resends before surfacing a stream error (default 8) |