claude-recall 0.34.1 → 0.34.2
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.
- package/README.md +5 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -141,6 +141,11 @@ claude-recall kiro setup --merge-into <agent-name>
|
|
|
141
141
|
- **It's a best-effort LLM judgement, not a guarantee.** The classifier decides what's a durable rule vs. chit-chat; it won't catch every phrasing, and near-identical wording can occasionally be judged differently. State preferences plainly ("use pnpm here, not npm") for the best hit rate.
|
|
142
142
|
- **There's a ~3s lag.** A preference you just stated isn't queryable for a couple of seconds while the worker finishes.
|
|
143
143
|
|
|
144
|
+
**Word your rules precisely — under Kiro this matters more.** Claude Code and Pi re-surface relevant rules right beside each tool call; Kiro has no channel for that, so rules act from a distance (session start + a refresh every 15 prompts). A vague rule tends to get overlooked mid-task; one that names the **trigger** and the **concrete pattern** gets applied. Real example, same session:
|
|
145
|
+
|
|
146
|
+
- ✗ *"name docs so they sort together in the file explorer"* → agent created `dummy_email.txt` anyway
|
|
147
|
+
- ✓ *"when creating a new file, match the naming prefix of similar files — email files are `email_*.txt`"* → agent named it correctly and cited the rule while doing it
|
|
148
|
+
|
|
144
149
|
**To verify capture actually worked** — from a second terminal (Kiro's chat can't shell out):
|
|
145
150
|
|
|
146
151
|
```bash
|
package/package.json
CHANGED