claude-recall 0.30.2 → 0.30.3
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 +31 -2
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -106,9 +106,38 @@ Already living in a custom agent of your own? Merge Claude Recall into it instea
|
|
|
106
106
|
claude-recall kiro setup --merge-into <agent-name>
|
|
107
107
|
```
|
|
108
108
|
|
|
109
|
-
> **⚠️
|
|
109
|
+
> **⚠️ You must start ONE fresh conversation after setup — this is the most common reason "it does nothing."**
|
|
110
|
+
>
|
|
111
|
+
> After `kiro setup` or `--merge-into`, start **one new conversation without `--resume`**:
|
|
112
|
+
>
|
|
113
|
+
> ```bash
|
|
114
|
+
> kiro-cli chat --agent recall # or: --agent <your-agent> if you merged
|
|
115
|
+
> ```
|
|
116
|
+
>
|
|
117
|
+
> Kiro snapshots the agent config at the moment a conversation is *created*. Any conversation that already existed — including one you reach with `--resume` or after restarting Kiro — was snapshotted **before** claude-recall was wired in, so it will **never** run the hooks and capture will silently do nothing. Once you've started that one fresh conversation, every conversation from then on carries the hooks and `--resume` works normally. This is a one-time rollover, once per project.
|
|
118
|
+
>
|
|
119
|
+
> Confirm the wiring is live before you rely on it:
|
|
120
|
+
>
|
|
121
|
+
> ```bash
|
|
122
|
+
> claude-recall kiro doctor # green checks = hooks are active for this project
|
|
123
|
+
> ```
|
|
124
|
+
|
|
125
|
+
**Capture runs on Kiro's own LLM — no API key, no personal subscription.** It classifies each prompt with a dedicated fixed model (default `claude-haiku-4.5`, independent of your chat model) and costs **~0.06 Kiro credits per prompt** — cheap, but note it's *every* prompt, so budget accordingly across a team.
|
|
126
|
+
|
|
127
|
+
**What to expect from capture — read this so it doesn't feel broken:**
|
|
128
|
+
|
|
129
|
+
- **It's silent and asynchronous.** Capture runs in a background worker so it never blocks your turn — which also means there's **no "captured ✓" message** in the Kiro chat. Stating a preference and seeing nothing happen is normal.
|
|
130
|
+
- **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.
|
|
131
|
+
- **There's a ~3s lag.** A preference you just stated isn't queryable for a couple of seconds while the worker finishes.
|
|
132
|
+
|
|
133
|
+
**To verify capture actually worked** — from a second terminal (Kiro's chat can't shell out):
|
|
134
|
+
|
|
135
|
+
```bash
|
|
136
|
+
claude-recall search "pnpm" # did the rule land?
|
|
137
|
+
tail -5 ~/.claude-recall/hook-logs/kiro-classifier.log # what the classifier decided, and which model ran
|
|
138
|
+
```
|
|
110
139
|
|
|
111
|
-
|
|
140
|
+
Or, from **inside the Kiro session**, just ask the agent to recall it (*"what do you remember about my package manager?"*) — it reads the same DB and will surface the stored rule if capture succeeded.
|
|
112
141
|
|
|
113
142
|
**Everything else Kiro** — MCP-only mode, project scoping and `--resume`, the classifier internals, enterprise-governance notes, troubleshooting: **[docs/kiro.md](docs/kiro.md)**.
|
|
114
143
|
|
package/package.json
CHANGED