pi-vault-mind 0.7.3 → 0.7.4

package/README.md

@@ -182,7 +182,15 @@ The Broadcaster agent can generate podcasts, study guides, and slide decks from
 - **Embedding Provider** — choose one:
   - `@xenova/transformers` — built-in, no external deps (uses all-MiniLM-L6-v2, offline-capable)
   - `ollama` — requires Ollama running locally with `embeddinggemma` (higher quality)
-  - `modal` — optional: offload embedding + bulk re-index to a cloud GPU service and sync vectors down for offline search (see [docs/MODAL_EMBEDDING.md](docs/MODAL_EMBEDDING.md)). Default behavior is unchanged until you opt in.
+  - `modal` — optional, **bring-your-own deploy**: offload embedding + bulk re-index to a cloud GPU service and sync vectors down for offline search (see [docs/MODAL_EMBEDDING.md](docs/MODAL_EMBEDDING.md)). Default behavior is unchanged until you opt in.
+
+> **On the Modal provider:** the local providers above work for everyone with
+> zero infrastructure — that's the default. `modal` is an **optional, self-hosted
+> tier**: you deploy your own copy of the service (`uvx modal deploy modal/app.py`
+> from a clone of this repo) to your own Modal account and point the extension at
+> *your* URL + token. There is no shared/hosted endpoint — a deployment's URL and
+> bearer token are private to whoever owns it. (A standalone PyPI package for the
+> server may come later.)
 
 ### 1. Install with pi
 
@@ -375,10 +383,8 @@ Edit `pi-vault-mind.config.json` to match your domain:
 |---|---|
 | [docs/AGENTS.md](docs/AGENTS.md) | Agent Roster and Multi-Agent Architecture ("Fork & Review" model) |
 | [docs/EXTENSION_WIRING.md](docs/EXTENSION_WIRING.md) | Extension dependencies, runtime wiring, auto-install patterns |
-| [docs/DISPATCHER_SPEC.md](docs/DISPATCHER_SPEC.md) | Technical spec for the passive file-watcher and subagent routing |
-| [docs/PASSIVE_INTERACTION_MODEL.md](docs/PASSIVE_INTERACTION_MODEL.md) | "Fork & Dispatch" model — why we don't pollute the main chat session |
-| [docs/PASSIVE_INGESTION_WORKFLOW.md](docs/PASSIVE_INGESTION_WORKFLOW.md) | The "Drop & Forget" document ingestion pipeline |
-| [docs/NOTEBOOKLM_PIPELINE.md](docs/NOTEBOOKLM_PIPELINE.md) | NotebookLM automated podcast and study guide generation |
+| [docs/DISPATCHER_SPEC.md](docs/DISPATCHER_SPEC.md) | Technical spec for the passive file-watcher and subagent routing — incl. the "Fork & Dispatch" rationale and thread resume |
+| [docs/AGENTS.md](docs/AGENTS.md) | Agent roster + the Miner's "Drop & Forget" ingestion pipeline |
 | [docs/OBSIDIAN_SETUP.md](docs/OBSIDIAN_SETUP.md) | Recommended Obsidian vault structure, plugins, and CLI |
 
 ### Modal embedding service (local integration done)

package/dist/test/index.test.d.ts

@@ -0,0 +1 @@
+export {};

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-vault-mind",
-  "version": "0.7.3",
+  "version": "0.7.4",
   "description": "Passive Obsidian vault extension for pi. Watches @agent markers, dispatches forked subagents (Miner, Broadcaster, Heavy-Lifter), stores in LanceDB with vector + FTS + graph. Multi-agent 'Drop & Forget' workflow for the pi agent ecosystem.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",