@shahmilsaari/memory-core 0.2.3 → 0.2.5

package/README.md

@@ -18,11 +18,10 @@ Without memory-core, every AI agent starts fresh. It doesn't know you're using C
 
 With memory-core:
 
-1. You run `init` once and answer a few questions about your project
-2. memory-core generates config files for every AI agent you use
-3. Those agents read the files and follow your rules — automatically
-4. When you commit code, a hook catches violations before they land in the repo
-5. Watch mode catches violations as you type, not just at commit time
+1. You run `init` once — it verifies your PostgreSQL and Ollama connections, picks your model, and generates config files for every AI agent
+2. Those agents read the files and follow your rules — automatically
+3. Watch mode catches violations as you type, not just at commit time
+4. When you commit, Claude Code automatically checks your code before the commit goes through
 
 ---
 
@@ -106,10 +105,10 @@ ollama serve &
 
 **Windows** — [download from ollama.com](https://ollama.com/download)
 
-Then pull the two models:
+Pull the embedding model. The code-checking model is chosen during `init`:
 ```bash
-ollama pull nomic-embed-text   # used for search
-ollama pull llama3.2           # used to check your code
+ollama pull nomic-embed-text   # required for search
+ollama pull llama3.2           # or whichever model you plan to use
 ```
 
 ---
@@ -153,14 +152,11 @@ CREATE INDEX IF NOT EXISTS memories_scope_idx ON memories (scope);
 # 1. Go to your project
 cd my-api
 
-# 2. Initialize — answers a few questions, generates all config files
+# 2. Initialize — verifies connections, picks your model, generates all config files
 npx @shahmilsaari/memory-core init
 
 # 3. Load 281 predefined best-practice rules
 npx @shahmilsaari/memory-core seed
-
-# 4. Install the pre-commit hook (optional but recommended)
-npx @shahmilsaari/memory-core hook install
 ```
 
 That's it. Every AI agent in your project now has your rules.
@@ -175,15 +171,18 @@ That's it. Every AI agent in your project now has your rules.
 npx @shahmilsaari/memory-core init
 ```
 
-Asks you:
-- Project name
-- Project type (Backend / Frontend / Fullstack)
-- Architecture (Clean Architecture, MVC, React, Vue, etc.)
-- Language
+Walks you through:
+- PostgreSQL connection URL — **tested live, retries until connected**
+- Ollama URL — **tested live, retries until reachable**
+- Code-checking model — **verified to be installed in your Ollama**
+- Project name, type, architecture, language
+- Whether to enable the pre-commit hook (asked during setup — no separate step needed)
 - Whether to enable caveman mode (optional token saver)
 
 Generates config files for every supported AI agent and saves your choices to `.memory-core.json`.
 
+At the end, the banner shows live ✓/✗ status for PostgreSQL and Ollama so you know everything is working.
+
 ---
 
 ### `remember` — Save a decision
@@ -253,7 +252,9 @@ npx @shahmilsaari/memory-core seed --force                     # re-seed existin
 npx @shahmilsaari/memory-core hook install
 ```
 
-Installs a git pre-commit hook. Every time you run `git commit`, your staged files are checked against your architecture rules before the commit goes through.
+Installs a git pre-commit hook in the current project. Every time you run `git commit`, your code is checked against your architecture rules before the commit goes through.
+
+> **Note:** If you use Claude Code, the hook is offered automatically during `init` — no separate step needed.
 
 When a violation is found, the commit is blocked and you see exactly what's wrong and how to fix it:
 
@@ -396,7 +397,7 @@ Pick the one that matches how your project is structured.
 | React | Functional components, hooks, React Query, Zustand |
 | Vue 3 | Composition API, Pinia, composables |
 | Angular | Standalone components, signals, OnPush strategy |
-| Svelte | Svelte 5 runes, SvelteKit load functions |
+| Svelte | Svelte 5 runes, SvelteKit load functions, snippets |
 | Nuxt 3 | Fullstack Vue with SSR |
 | React Native | Mobile apps |
 
@@ -421,9 +422,8 @@ Cuts AI response length by 65–75% by removing filler words. Opt in during `ini
 ```bash
 # Starting a new project
 cd my-api
-npx @shahmilsaari/memory-core init
-npx @shahmilsaari/memory-core seed
-npx @shahmilsaari/memory-core hook install
+npx @shahmilsaari/memory-core init   # verifies connections, picks model, installs hook
+npx @shahmilsaari/memory-core seed   # load 281 best-practice rules
 
 # Made an architectural decision? Save it.
 npx @shahmilsaari/memory-core remember "All auth goes through middleware, never in controllers" \
@@ -435,7 +435,7 @@ npx @shahmilsaari/memory-core sync
 # Not sure how something was decided? Search.
 npx @shahmilsaari/memory-core search "caching strategy"
 
-# Commit code → hook checks it automatically
+# Commit code → Claude Code checks it automatically before committing
 git commit -m "add user endpoint"
 ```
 
@@ -449,8 +449,8 @@ memory-core creates `.memory-core.env` automatically during `init`. You can also
 |---|---|---|---|
 | `DATABASE_URL` | Yes | — | PostgreSQL connection string |
 | `OLLAMA_URL` | No | `http://localhost:11434` | Where Ollama is running |
-| `OLLAMA_MODEL` | No | `nomic-embed-text` | Model used for search |
-| `OLLAMA_CHAT_MODEL` | No | `llama3.2` | Model used for code checking |
+| `OLLAMA_MODEL` | No | `nomic-embed-text` | Model used for search (embeddings) |
+| `OLLAMA_CHAT_MODEL` | No | `llama3.2` | Model used for code checking — chosen during `init` |
 
 ---
 
@@ -483,6 +483,10 @@ It won't — the hook only checks source code files: `.ts .tsx .js .jsx .py .php
 | | Feature |
 |---|---|
 | ✓ | Watch mode — real-time violation alerts on save |
+| ✓ | Model picker — choose your Ollama model during init |
+| ✓ | Connection validation — PostgreSQL and Ollama verified during setup |
+| ✓ | Svelte 5 / SvelteKit profile and 37 rules |
+| ✓ | NestJS profile and 39 rules |
 | | CI/CD — fail PRs that violate your rules |
 | | Violation memory — auto-save what went wrong as a new rule |
 | | Rule analytics — see which rules get broken most |
@@ -494,3 +498,5 @@ It won't — the hook only checks source code files: `.ts .tsx .js .jsx .py .php
 ## License
 
 MIT
+
+*Built by [Shahmil Saari](https://github.com/shahmilsaari)*

package/dist/cli.js

@@ -699,6 +699,20 @@ import { execSync } from "child_process";
 import { writeFileSync as writeFileSync2, existsSync as existsSync4, unlinkSync, readFileSync as readFileSync3, chmodSync } from "fs";
 import { join as join4 } from "path";
 import chalk from "chalk";
+async function resolveModel(ollamaUrl, chatModel) {
+  try {
+    const res = await fetch(`${ollamaUrl}/api/tags`, { signal: AbortSignal.timeout(3e3) });
+    if (!res.ok) return chatModel;
+    const data = await res.json();
+    const models = data.models ?? [];
+    const exact = models.find((m) => m.name === chatModel);
+    if (exact) return exact.name;
+    const prefixed = models.find((m) => m.name.startsWith(`${chatModel}:`));
+    if (prefixed) return prefixed.name;
+  } catch {
+  }
+  return chatModel;
+}
 var reasonMap = new Map(
   seeds.filter((s) => s.reason).map((s) => [s.content, s.reason])
 );
@@ -794,7 +808,7 @@ async function checkStaged(options = {}) {
   }
   if (rules.length === 0) return;
   const ollamaUrl = process.env.OLLAMA_URL ?? "http://localhost:11434";
-  const chatModel = process.env.OLLAMA_CHAT_MODEL ?? "llama3.2";
+  const chatModel = await resolveModel(ollamaUrl, process.env.OLLAMA_CHAT_MODEL ?? "llama3.2");
   const MAX_DIFF = 8e3;
   const truncated = diff.length > MAX_DIFF;
   const diffToSend = truncated ? diff.slice(0, MAX_DIFF) + "\n\n[diff truncated]" : diff;
@@ -918,6 +932,20 @@ import { execSync as execSync2 } from "child_process";
 import { existsSync as existsSync5, readFileSync as readFileSync4 } from "fs";
 import { join as join5, relative } from "path";
 import chalk2 from "chalk";
+async function resolveModel2(ollamaUrl, chatModel) {
+  try {
+    const res = await fetch(`${ollamaUrl}/api/tags`, { signal: AbortSignal.timeout(3e3) });
+    if (!res.ok) return chatModel;
+    const data = await res.json();
+    const models = data.models ?? [];
+    const exact = models.find((m) => m.name === chatModel);
+    if (exact) return exact.name;
+    const prefixed = models.find((m) => m.name.startsWith(`${chatModel}:`));
+    if (prefixed) return prefixed.name;
+  } catch {
+  }
+  return chatModel;
+}
 function getFileLines(filePath) {
   try {
     return readFileSync4(filePath, "utf-8").split("\n");
@@ -993,7 +1021,7 @@ async function checkFile(filePath, cwd, config2, verbose) {
   const { rules, avoids } = getProfileRules(config2);
   if (rules.length === 0) return;
   const ollamaUrl = process.env.OLLAMA_URL ?? "http://localhost:11434";
-  const chatModel = process.env.OLLAMA_CHAT_MODEL ?? "llama3.2";
+  const chatModel = await resolveModel2(ollamaUrl, process.env.OLLAMA_CHAT_MODEL ?? "llama3.2");
   const MAX_DIFF = 6e3;
   const truncated = diff.length > MAX_DIFF;
   const diffToSend = truncated ? diff.slice(0, MAX_DIFF) + "\n\n[diff truncated]" : diff;
@@ -1092,7 +1120,7 @@ ${diffToSend}` }
     }
   }
 }
-function startWatch(options = {}) {
+async function startWatch(options = {}) {
   const cwd = process.cwd();
   const config2 = loadConfig(cwd);
   if (!config2) {
@@ -1106,7 +1134,7 @@ function startWatch(options = {}) {
   }
   const watchPath = options.path ?? cwd;
   const ollamaUrl = process.env.OLLAMA_URL ?? "http://localhost:11434";
-  const chatModel = process.env.OLLAMA_CHAT_MODEL ?? "llama3.2";
+  const chatModel = await resolveModel2(ollamaUrl, process.env.OLLAMA_CHAT_MODEL ?? "llama3.2");
   console.log(chalk2.cyan("\n  archmind watch \u2014 real-time rule enforcement\n"));
   console.log(chalk2.dim(`  watching: ${watchPath}`));
   console.log(chalk2.dim(`  model:    ${chatModel}`));
@@ -1304,10 +1332,12 @@ program.command("init").description("Initialize memory-core in the current proje
       try {
         const res = await fetch(`${ollamaUrl}/api/tags`, { signal: AbortSignal.timeout(5e3) });
         const data = await res.json();
-        const installed = (data.models ?? []).some(
-          (m) => m.name === chatModel || m.name.startsWith(`${chatModel}:`)
-        );
-        if (installed) {
+        const models = data.models ?? [];
+        const exact = models.find((m) => m.name === chatModel);
+        const prefixed = models.find((m) => m.name.startsWith(`${chatModel}:`));
+        const match = exact ?? prefixed;
+        if (match) {
+          chatModel = match.name;
           modelSpinner.succeed(chalk3.green(`${chatModel} is installed and ready`));
           break;
         } else {
@@ -1400,6 +1430,10 @@ program.command("init").description("Initialize memory-core in the current proje
       ]
     });
   }
+  const enableHook = await confirm({
+    message: "Enable pre-commit hook? (blocks commits that violate your rules)",
+    default: true
+  });
   const config2 = {
     projectName,
     projectType,
@@ -1438,6 +1472,9 @@ program.command("init").description("Initialize memory-core in the current proje
   );
   writeProjectConfig(config2);
   spinner.succeed(`Generated ${written.length} files`);
+  if (enableHook) {
+    installHook();
+  }
   const status = await checkConnections(
     process.env.DATABASE_URL ?? "",
     process.env.OLLAMA_URL ?? "http://localhost:11434",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@shahmilsaari/memory-core",
-  "version": "0.2.3",
+  "version": "0.2.5",
   "description": "Universal AI memory core — generate AI context files from architecture profiles with RAG support",
   "type": "module",
   "bin": {