docdex 0.2.75 → 0.2.77

package/CHANGELOG.md

@@ -1,5 +1,17 @@
 # Changelog
 
+## Unreleased
+
+## 0.2.77
+- Fix packaged setup CLI help so `docdexd setup --help` describes provider-neutral local LLM service detection and optional fallbacks instead of an Ollama-first wizard.
+- Sync packaged MCP server-card release metadata with the package version and add regression coverage for MCP/package metadata drift.
+- Bump packaged release metadata to 0.2.77.
+
+## 0.2.76
+- Add packaged provider-neutral local LLM setup and diagnostics guidance so npm installs do not imply Ollama is mandatory when another supported local service or mcoda agent already exists.
+- Add packaged migration/test coverage notes for preserving explicit user model/provider/agent settings while replacing generated legacy Ollama defaults.
+- Bump packaged release metadata to 0.2.76.
+
 ## 0.2.75
 - Add packaged automatic AI-terminal capture, generated-skill registry, validation, sync, install, rollback, and context-hint surfaces for personal-preferences and mind-clone workflows.
 - Add packaged generated-skill quality reports with replay, drift, stale-source, activation feedback, and promote/keep/review/demote/quarantine recommendations.

package/README.md

@@ -34,7 +34,7 @@ Most AI tools rely on "grep" (fast but dumb) or hosted RAG (slow and requires up
 * **💾 Repo Memory:** Stores project facts, decisions, and notes locally.
 * **👤 Agent Memory:** Remembers user preferences (e.g., "Use concise bullet points") across different repositories.
 * **🔌 MCP Native:** Auto-configures for tools like Claude Desktop, Cursor, and Windsurf.
-* **🌐 Web Enrichment:** Optional web search with local LLM filtering (via Ollama).
+* **🌐 Web Enrichment:** Optional web search with local LLM filtering through detected local LLM services.
 
 ---
 
@@ -212,13 +212,14 @@ docdexd profile add --agent-id "default" --category style --content "Use concise
 
 ```
 
-### 3. Local LLM (Ollama)
+### 3. Local LLM Services
 
-Docdex uses Ollama for embeddings and optional local chat.
+Docdex detects supported local LLM services before it suggests installing anything. It can reuse Ollama, vLLM, llama.cpp-compatible OpenAI endpoints, LM Studio, LocalAI, SGLang, TGI-compatible deployments, and healthy local mcoda agents when they are already present. Ollama remains the recommended fallback because it is the easiest guided setup path.
 
-* **Setup:** Run `docdex setup` for an interactive wizard.
-* **Manual:** Ensure `nomic-embed-text` is pulled in Ollama (`ollama pull nomic-embed-text`).
-* **Custom URL:**
+* **Setup:** Run `docdex setup` for an interactive wizard that lists detected services, models, embedding candidates, and local delegation agents.
+* **Inspect:** Run `docdexd llm detect --json` or `docdexd llm diagnostics --json` to see why a service/model was selected, skipped, or marked unhealthy.
+* **Manual Ollama fallback:** If no usable service is installed, pull the fallback embedding model with `ollama pull nomic-embed-text`.
+* **Custom Ollama URL:**
 ```bash
 DOCDEX_OLLAMA_BASE_URL=http://127.0.0.1:11434 docdexd daemon --host 127.0.0.1 --port 28491
 

package/assets/agents.md

@@ -1,4 +1,4 @@
----- START OF DOCDEX INFO V0.2.75 ----
+---- START OF DOCDEX INFO V0.2.77 ----
 Docdex URL: http://127.0.0.1:28491
 Use this base URL for Docdex HTTP endpoints.
 Health check endpoint: `GET /healthz` (not `/v1/health`).

package/lib/install.js

@@ -2433,7 +2433,7 @@ function printPostInstallBanner() {
     const plain = [
       "[docdex] Docdex installed successfully.",
       "[docdex] Next step: run `docdex setup` to complete the installation.",
-      "[docdex] Setup configures Ollama/models + browser."
+      "[docdex] Setup detects local LLM services, offers the Ollama fallback, and configures browser."
     ].join("\r\n") + "\r\n";
     if (!writeDirect(plain)) {
       writeStderr(plain);
@@ -2449,7 +2449,7 @@ function printPostInstallBanner() {
     "",
     "\x1b[32mDocdex installed successfully!\x1b[0m",
     "\x1b[41m\x1b[97m IMPORTANT \x1b[0m \x1b[33mNext step:\x1b[0m run \x1b[32m`docdex setup`\x1b[0m to complete the installation.",
-    "\x1b[33mSetup:\x1b[0m configures Ollama/models + browser.",
+    "\x1b[33mSetup:\x1b[0m detects local LLM services, offers the Ollama fallback, and configures browser.",
     "\x1b[34mTip:\x1b[0m after setup, the daemon should auto-start; if not, run \x1b[36m`docdexd daemon`\x1b[0m"
   ];
   if (process.platform === "win32") {

package/lib/postinstall_setup.js

@@ -3057,7 +3057,13 @@ async function runPostInstallSetup({ binaryPath, logger, env, skipDaemon, distBa
   if (!setupLaunch.ok) {
     if (setupLaunch.reason !== "skipped") {
       log.warn?.("[docdex] setup wizard did not launch. Run `docdex setup`.");
-      recordSetupPending({ reason: setupLaunch.reason, port, repoRoot: daemonRoot });
+      log.warn?.("[docdex] `docdex setup` will detect existing local LLM services before offering the Ollama fallback.");
+      recordSetupPending({
+        reason: setupLaunch.reason,
+        port,
+        repoRoot: daemonRoot,
+        setup: "local_llm_service_choice"
+      });
     }
   }
   return { port, url, configPath };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "docdex",
-  "version": "0.2.75",
+  "version": "0.2.77",
   "mcpName": "io.github.bekirdag/docdex",
   "description": "Local-first documentation and code indexer with HTTP/MCP search, AST, and agent memory.",
   "bin": {