@agile-vibe-coding/avc 0.3.2 → 0.3.4

package/README.md

@@ -4,6 +4,39 @@
 
 AVC is a toolkit — combining a command-line interface with an interactive web-based kanban board — that implements the principles of the [Agile Vibe Coding Manifesto](https://agilevibecoding.org). It provides ceremonies, assets, and validation workflows that guide AI coding agents toward coherent, long-term software delivery — shaping context, constraints, and verification so that LLM limitations don't silently degrade your project.
 
+> **PROJECT STATUS — EARLY BETA**
+>
+> AVC structures AI-assisted development through **ceremonies** — guided workflows that decompose project scope into traceable, validated work items before any code is written. The goal is structured, auditable AI coding aligned with the [Agile Vibe Coding Principles](https://agilevibecoding.org). Ceremony status:
+>
+> | Ceremony | Status | Notes |
+> |----------|--------|-------|
+> | **Sponsor Call** | Pre-production | Functional, tested across multiple projects and LLM providers |
+> | **Sprint Planning** | Pre-production | Functional, includes decomposition, validation, context generation, and scaffolding |
+> | **Seed** | Under development | Task/subtask decomposition works, validation loop in progress |
+> | **Run** | Under development | Worktree lifecycle and code generation designed, not yet production-tested |
+>
+> ### What We Need From Beta Testers
+>
+> If you try **Sponsor Call** or **Sprint Planning**, we'd appreciate feedback on:
+>
+> - **Quality of generated documentation** — Does the `doc.md` accurately capture your project? Are there hallucinations or missing sections?
+> - **Decomposition accuracy** — Do the Epics and Stories make sense for your project? Are there scope overlaps, missing features, or over-decomposition?
+> - **Dependency correctness** — Are the dependency chains between epics/stories logical? Can they be implemented in the computed order?
+> - **Validation usefulness** — Do the micro-check scores and auto-fixes improve quality, or do they feel like noise?
+> - **Model/provider experience** — Which provider worked best for your project size and complexity?
+>
+> Report bugs, feature requests, and ideas at [github.com/NachoColl/agilevibecoding/issues](https://github.com/NachoColl/agilevibecoding/issues) — all feedback from early testers helps shape the tool.
+>
+> ### Model Setup
+>
+> AVC requires at least one LLM provider API key. After running `/init`, go to **Settings > API Keys** in the kanban board to add your key.
+>
+> - **Claude** (Anthropic), **Gemini** (Google), **OpenAI** — production-grade cloud providers. Best quality and speed.
+> - **Xiaomi MiMo** — proving to be very cost-efficient. MiMo V2 Pro ($1/$3 per 1M tokens) handles decomposition and documentation well. MiMo V2 Flash ($0.09/$0.29) works for validation. A full Sprint Planning ceremony costs ~$0.05-0.15. Get a key at [platform.xiaomimimo.com](https://platform.xiaomimimo.com).
+> - **Local LLMs** (LM Studio / Ollama) — supported but **very slow on regular laptops** (a Sprint Planning ceremony can take 30+ minutes vs 3-5 minutes with cloud providers). Useful for experimentation without API costs.
+>
+> AVC auto-detects which provider has a key and configures all ceremony stages accordingly — you only need one key to get started.
+
 ## How to Install
 
 ```bash
@@ -18,12 +51,11 @@ avc
 
 This launches the AVC interactive CLI. From there:
 
-1. Run `/init` to initialize AVC in your project (creates `.avc/` config directory and `.env` for API keys)
-2. Run `/kanban` to launch the web-based kanban board at `http://localhost:4174`
-3. From the kanban board, configure your LLM provider in **Settings** (API keys, ceremony models)
-4. Start the **Sponsor Call** ceremony to define your project scope
-5. Run **Sprint Planning** to decompose into Epics and Stories
-6. Use **Seed** to break Stories into Tasks, then **Run** to implement code
+1. Run `/init` to initialize AVC in your project — this creates the `.avc/` config directory, `.env` for API keys, and automatically launches the kanban board at `http://localhost:4174`
+2. From the kanban board, configure your LLM provider in **Settings** (API keys, ceremony models)
+3. Start the **Sponsor Call** ceremony to define your project scope
+4. Run **Sprint Planning** to decompose into Epics and Stories
+5. Use **Seed** to break Stories into Tasks, then **Run** to implement code
 
 AVC auto-detects available API keys and switches ceremony models accordingly — if only one provider key is set, all ceremonies use that provider automatically.
 

package/cli/seed-processor.js

@@ -895,7 +895,6 @@ Return your response as JSON following the exact structure specified in your ins
       throw error;
     }
   }
-}
 
   /**
    * Worker-compatible execution — uses callbacks instead of REPL output functions.