claude-smart 0.1.6 → 0.1.8

package/README.md

@@ -6,14 +6,14 @@
   claude-smart
 </h1>
 
-<h4 align="center">The <a href="https://claude.com/claude-code" target="_blank">Claude Code</a> plugin that makes Claude Code self-improve as you use it — not by remembering past sessions, but by turning your corrections into rules it actually follows next time.</h4>
+<h4 align="center">The <a href="https://claude.com/claude-code" target="_blank">Claude Code</a> plugin that makes Claude Code self-improve as you use it — not by remembering past sessions, but by turning your corrections into playbooks it actually follows next time.</h4>
 
 <p align="center">
   <a href="LICENSE">
     <img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="License">
   </a>
   <a href="plugin/pyproject.toml">
-    <img src="https://img.shields.io/badge/version-0.1.6-green.svg" alt="Version">
+    <img src="https://img.shields.io/badge/version-0.1.8-green.svg" alt="Version">
   </a>
   <a href="plugin/pyproject.toml">
     <img src="https://img.shields.io/badge/python-%3E%3D3.12-brightgreen.svg" alt="Python">
@@ -32,7 +32,7 @@
   <a href="#slash-commands">Slash Commands</a> •
   <a href="#dashboard">Dashboard</a> •
   <a href="#configuration">Configuration</a> •
-  <a href="#troubleshooting">Troubleshooting</a> •
+  <a href="TROUBLESHOOTING.md">Troubleshooting</a> •
   <a href="#license">License</a>
 </p>
 
@@ -47,13 +47,13 @@
 
 ## Why Learning, Not Memory
 
-Most memory solutions re-inject transcripts or summaries from prior sessions, but it is still mostly informative—Claude remembers what happened, without necessarily changing what it does next.
+Most memory solutions are still mostly informative—Claude remembers what happened, without necessarily changing what it does next.
 
 `claude-smart` focuses on learning instead.
 
 Four ways this changes what Claude Code can do for you:
 
-- **Actionable, not just informative:** Produces rules Claude can follow next time; memory only records what happened; 
+- **Actionable, not just informative:** Produces playbooks Claude can follow next time; memory only records what happened.
 
   > *Example:* you tell Claude to stop running `npm test` without `--run` because watch mode hangs.
   > **Memory:** “user was annoyed about npm test hanging”
@@ -68,7 +68,7 @@ Four ways this changes what Claude Code can do for you:
 
 - **Project-wide, not session-siloed:** Session memory disappears with the conversation. The project playbook persists and improves across every session in that repo.
 
-- **Compact:** Distilled, deduplicated rules stay in dozens of tokens—not thousands—even as the project grows.
+- **Compact:** Distilled, deduplicated playbooks stay in dozens of tokens—not thousands—even as the project grows.
 
 claude-smart turns corrections and successful execution patterns into two artifacts:
 
@@ -85,16 +85,28 @@ Both are automatically reinjected at the start of every session, so Claude Code
 npx claude-smart install     # or: uvx claude-smart install
 ```
 
-Or run the equivalent marketplace commands directly inside Claude Code:
+Or run the equivalent marketplace commands directly via the Claude Code CLI:
 
-```text
-/plugin marketplace add ReflexioAI/claude-smart
-/plugin install claude-smart@reflexioai
+```bash
+claude plugin marketplace add ReflexioAI/claude-smart
+claude plugin install claude-smart@reflexioai
 ```
 
 Then restart Claude Code.
 
-To uninstall: `/plugin uninstall claude-smart@reflexioai`.
+To uninstall:
+
+```bash
+npx claude-smart uninstall     # or: uvx claude-smart uninstall
+```
+
+Or run the equivalent command directly via the Claude Code CLI:
+
+```bash
+claude plugin uninstall claude-smart@reflexioai
+```
+
+Local data under `~/.reflexio/` and `~/.claude-smart/` is left in place — remove manually if desired.
 
 Developing the plugin itself? See [DEVELOPER.md](./DEVELOPER.md#developing-locally).
 
@@ -104,7 +116,7 @@ Developing the plugin itself? See [DEVELOPER.md](./DEVELOPER.md#developing-local
 
 - 🧠 **Learn, don't just remember** — Corrections become structured, deduplicated rules, not transcript replays.
 - ⚡ **Fully automatic learning** — Every user turn, tool call, and assistant response is captured via lifecycle hooks and extracted into rules without you running anything.
-- 📈 **Compounds with every session** — Rules auto-merge, supersede, and archive as your project evolves — the playbook sharpens with use instead of bloating.
+- 📈 **Updates with every session** — Playbooks auto-merge, supersede, and archive as your project evolves — the playbook sharpens with use instead of bloating.
   > *e.g.* you correct the same `npm test --run` gotcha twice → **claude-smart** consolidates them into one stronger rule. Later you switch the policy to `pnpm test` → the old rule is archived and the new one supersedes it, no manual cleanup.
 - 🎯 **Two-tier scope** — Per-session profiles for the current conversation; cross-session playbooks for the whole project.
 - 🔌 **No external API call** — semantic search runs on an in-process ONNX embedder (all-MiniLM-L6-v2), and all data (profiles, playbooks, interaction buffers) is stored locally on your machine (`~/.reflexio/` and `~/.claude-smart/`).
@@ -132,7 +144,7 @@ claude-smart builds two artifacts as you work and injects them into Claude at th
 - **User profile** — session-scoped preferences (stack, role, small quirks). *e.g.* "uses pnpm, not npm"; "prefers terse answers"; "backend engineer — explain frontend with backend analogues."
 - **Project playbook** — durable, generalized rules accumulated across every session in the repo. Each says when it applies and why. *e.g.* "always pass `--run` to `npm test` — watch mode hangs CI"; "use real Postgres for integration tests — mocks once hid a broken migration."
 
-Rules clean themselves up: correct the same thing twice and they merge; change your mind and the old one is archived.
+Playbooks clean themselves up: correct the same thing twice and they merge; change your mind and the old one is archived.
 
 Under the hood: hooks watch your turns, tool calls, and Claude's replies, auto-flagging corrections (or anything you `/tag`). At session end (or on `/learn`), [reflexio](https://github.com/ReflexioAI/reflexio) — the self-improving engine that powers claude-smart — extracts profile entries and playbook rules. Next session, both get injected into the system prompt — run `/show` to see what Claude is being told. Everything runs on your machine.
 
@@ -144,7 +156,7 @@ See [ARCHITECTURE.md](./ARCHITECTURE.md) for hooks, data flow, and reflexio deta
 
 | Command | What it does |
 | --- | --- |
-| `/show` | Print the current project playbook plus the current session's user profiles (same markdown that `SessionStart` injects). Use it to audit what rules and preferences Claude is being told to follow. |
+| `/show` | Print the current project playbook plus the current session's user profiles (same markdown that `SessionStart` injects). Use it to audit what playbooks and preferences Claude is being told to follow. |
 | `/learn` | Force reflexio to run extraction *now* on the current session's unpublished interactions. Without this, extraction runs at the end of the session or on reflexio's batch interval. |
 | `/tag [note]` | Tag the most recent turn as a correction, for cases the automatic heuristic missed. The note becomes the correction description the extractor sees. |
 | `/restart` | Restart the reflexio backend and dashboard to pick up new changes (e.g. after upgrading the plugin or editing local reflexio code). |
@@ -165,36 +177,7 @@ Advanced users can tune claude-smart via environment variables — see [DEVELOPE
 | `~/.claude-smart/sessions/{session_id}.jsonl` | Per-session buffer. User turns, assistant turns, tool invocations, `{"published_up_to": N}` watermarks. Safe to inspect and safe to delete — everything past the latest watermark has already been written to reflexio's DB. |
 | `~/.cache/chroma/onnx_models/all-MiniLM-L6-v2/` | Cached ONNX weights (~86 MB, downloaded once). Delete to force a re-download. |
 
-### Embeddings
-
-claude-smart uses an in-process ONNX embedder (Chroma's `all-MiniLM-L6-v2`, 384-dim, zero-padded to reflexio's 512-dim schema). The model weights are downloaded on first use (~80 MB, cached under `~/.cache/chroma/onnx_models/`) — after that, no network calls for embedding. Runtime cost is a few milliseconds per short document on CPU.
-
-If you still want to use a cloud embedding provider (OpenAI, Gemini, etc.), omit `CLAUDE_SMART_USE_LOCAL_EMBEDDING` and set the corresponding API key in `~/.reflexio/.env` — reflexio will fall back to its standard provider-priority chain.
-
----
-
-## Troubleshooting
-
-**SessionStart injects nothing after a correction.**
-Extraction is async by default. Run `/learn` to force it, wait ~20–30s, then run `/show` — no new session needed. `/show` shows whether the rule was actually extracted.
-
-**Reflexio refuses to boot with "no embedding-capable provider".**
-Check that `CLAUDE_SMART_USE_LOCAL_EMBEDDING=1` is in `~/.reflexio/.env` *and* that `chromadb` is installed in the venv (`uv run --project plugin python -c "import chromadb"` should print nothing). If you'd rather use a cloud embedder instead, drop the env flag and set `OPENAI_API_KEY` or `GEMINI_API_KEY` in the same file.
-
-**`claude-smart` doesn't see my interactions.**
-Check `~/.claude-smart/sessions/`. If your current session's JSONL has no `User`/`Assistant` rows, the plugin isn't receiving hook events — verify `.claude/settings.local.json` has the right path and that `enabledPlugins` is `true`.
-
-**Hooks appear to time out.**
-Each hook is capped at 15–60s. If you see long pauses, check `uv` is on PATH (hooks shell out to `uv run`). Set `CLAUDE_SMART_CLI_TIMEOUT=180` to give the LLM provider more headroom.
-
-**A different LLM is being used.**
-Reflexio's provider priority is `claude-code > local > anthropic > gemini > ... > openai`. If you have `CLAUDE_SMART_USE_LOCAL_CLI=1` *and* an Anthropic key set, claude-code still wins for generation; `local` sits above openai/gemini for embeddings. Check the startup log line `Primary provider for generation: <name>` and `Embedding provider: <name>` to confirm.
-
-**I want to wipe everything and start over.**
-```bash
-rm -rf ~/.claude-smart/sessions/
-rm -rf ~/.reflexio/data/           # reflexio SQLite store
-```
+For troubleshooting, see [TROUBLESHOOTING.md](./TROUBLESHOOTING.md).
 
 ---
 

package/bin/claude-smart.js

@@ -61,6 +61,9 @@ function printHelp() {
       "Update:",
       "  npx claude-smart update                        Update to the latest version",
       "",
+      "Uninstall:",
+      "  npx claude-smart uninstall                     Remove the plugin from Claude Code",
+      "",
     ].join("\n"),
   );
 }
@@ -96,6 +99,35 @@ function runUpdate() {
   process.stdout.write("\nclaude-smart updated. Restart Claude Code to apply.\n");
 }
 
+function runUninstall() {
+  if (!hasClaudeCli()) {
+    process.stderr.write(
+      "error: 'claude' CLI not found on PATH. " +
+        "Install Claude Code first: https://claude.com/claude-code\n",
+    );
+    process.exit(1);
+  }
+
+  try {
+    execFileSync("claude", ["plugin", "uninstall", PLUGIN_SPEC], { stdio: "inherit" });
+  } catch (err) {
+    const code = typeof err.status === "number" ? err.status : 1;
+    process.stderr.write(
+      `error: \`claude plugin uninstall ${PLUGIN_SPEC}\` failed (exit ${code})\n`,
+    );
+    process.exit(code);
+  }
+
+  process.stdout.write(
+    [
+      "",
+      "claude-smart uninstalled. Restart Claude Code to apply.",
+      "Local data in ~/.reflexio/ and ~/.claude-smart/ was left in place — remove manually if desired.",
+      "",
+    ].join("\n"),
+  );
+}
+
 function runInstall(args) {
   if (!hasClaudeCli()) {
     process.stderr.write(
@@ -160,6 +192,11 @@ function main() {
     return;
   }
 
+  if (cmd === "uninstall") {
+    runUninstall();
+    return;
+  }
+
   process.stderr.write(
     `claude-smart: unknown command '${cmd}'. Try 'npx claude-smart --help'.\n`,
   );

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-smart",
-  "version": "0.1.6",
+  "version": "0.1.8",
   "description": "Self-improving Claude Code plugin — learns from corrections via reflexio",
   "keywords": [
     "claude",