hablas-ai 1.3.21 → 2.0.0

package/CHANGELOG.md

@@ -1,158 +1,32 @@
 # Changelog
 
-All notable changes to **Hablas CLI** will be documented in this file.
+## [2.0.0] — 2026-06-12 · Full Single-Agent Rebuild
 
-The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
-and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
-
----
-
-## [1.3.21] — 2026-06-12 · Leader-Only UX Hotfix
-
-### Fixed
-- Stopped unified runtime debug payloads from appearing in normal user output.
-- Hid internal team theatre by default in the stable line.
-- Preserved internal coordinated execution while keeping **Hablas** as the only visible user-facing speaker.
-- Replaced visible delegation noise with cleaner coordination status during team execution.
-- Tightened Hablas tone to avoid emojis, hype, and filler in normal responses.
-
-### Notes
-- Internal team theatre is now debug-only and can be re-enabled explicitly for inspection.
-- This hotfix targets the reported regression where continuity/team routing leaked internal execution UX to the user.
-
-## [1.3.20] — 2026-06-12 · Stable Runtime Recovery
-
-### Changed
-- Removed public mode-era commands from the stable CLI surface:
-  - `hablas build`
-  - `hablas design`
-  - `hablas ask`
-  - `/mode`
-- Re-centered the product around a **single command surface**:
-  - `hablas`
-  - `hablas run "..."`
-- Replaced visible mode thinking with an internal unified runtime model based on:
-  - `executionPath: direct | team`
-  - `taskKind: conversation | analysis | implementation`
-- Updated the interactive REPL and non-interactive `run` command to enter through the unified runtime path first.
-- Simplified setup and help messaging to match the stable mental model.
-
-### Removed
-- Hidden gate-based routing from the active stable-line code path.
-- Gate defaults from agent model configuration.
-- Gate mindset registration from the built-in mindset registry.
-
-### Added
-- Unified runtime regression smoke tests covering:
-  - direct casual handling
-  - direct quick questions
-  - team analysis routing
-  - continuity routing
-  - one-step delivery routing
-- Stable runtime recovery documentation in:
-  - `docs/stable-runtime-recovery-plan-2026-06-12.md`
-
-### Verified
-- `npm test` passes
-- `npm run build` passes
-- CLI help no longer exposes removed public mode commands
-
-## [1.0.0] — 2026-05-31 · **First Public Release**
-
-The first formal, polished, production-ready release of Hablas CLI. Months of
-internal iteration consolidated into a focused, type-strict, dead-code-free
-multi-agent system that runs locally or against any OpenAI-compatible API.
-
-### ✨ Highlights
-- **Live Team Theatre** — watch the multi-agent team (Hablas → Emma → Bob →
-  Alex → David) collaborate in real time, in character, with bounded
-  in-character dialogue between agents.
-- **Single-leader UX** — you only talk to Hablas. He delegates, reviews,
-  synthesizes, and replies in his own INTJ voice.
-- **Strict separation of concerns** — `AgentChannel` (event bus),
-  `TheatreRenderer` (UI), `TeamConductor` (orchestration logic),
-  `InterAgentChat` (dialogue generation) are fully decoupled.
+This release replaces the old stable product surface with a new one built around a strict single-agent direction.
 
 ### Added
-- **Live Team Theatre subsystem** (5 new modules, ~1,000 LOC):
-  - `agents/agent-channel.ts` — typed event bus, single source of truth.
-  - `agents/inter-agent-chat.ts` — bounded in-character dialogue generator
-    with token budget, cache, and deterministic fallback.
-  - `agents/team-conductor.ts` — drives delegate → handoff → execute →
-    peer-review → synthesize on the AgentChannel.
-  - `repl/theatre.ts` — executive-silver TUI subscriber.
-  - `agents/__tests__/agent-channel.test.ts` — 11 unit tests.
-- **T-shirt sizing** (XS/S/M/L/XL) for complexity-aware routing.
-- **Plan approval flow** with `approve / edit / skip` for L and XL tasks.
-- **`/team`, `/agents`, `/agents models`, `/delegate`** slash commands.
-- **Multi-provider support** — Ollama, NVIDIA NIM, OpenAI-compatible APIs.
-- **Tool Parser V2** — model-aware learning across 6+ tool-call formats.
-- **ReAct engine** with `<thinking>` block parsing and step budget warnings.
-- **Error Recovery engine** — classifies tool failures and injects
-  recovery strategies into the next prompt.
-- **Smart abort** — only critical tool failures stop the chain.
-- **Ctrl+C** — single press cancels the current op, double press exits cleanly.
-- **Checkpoint & Undo Stack** — `/checkpoint save|list|restore`, `/undo [all|list|N]`.
-- **Project memory** — categorized, importance-weighted, decay-based, agent-lanes.
-- **Auto-inject** — files mentioned in user input are auto-loaded into the session.
-- **Setup wizard** on first run.
-- **Team mode** (`--team`) — Supabase + Git-based file locks and presence.
-- **`hablas commit | pr | changelog | security | stats | info`** sub-commands.
+- new single-agent CLI entry
+- new single-agent interactive runtime
+- new task analyzer
+- new prompt builder
+- new direct text-turn path
+- new rebuild-oriented docs set
+- analyzer regression test
+- engine smoke test retained around the canonical execution loop
 
 ### Changed
-- **`package.json` version** bumped from internal `2.0.0` to public `1.0.0`.
-- **README** updated for the v1.0.0 release.
-- **`tsconfig.json`** hardened: enabled `noUnusedLocals`,
-  `noUnusedParameters`, `noImplicitOverride`,
-  `noFallthroughCasesInSwitch`.
-
-### Removed (cleanup)
-- **37 dead-code files** (~6,000 LOC) — abandoned v1/v2/v3 variants,
-  unfinished subsystems, type shims for unused dependencies. Concretely:
-  - `agents/{research-agent, self-evaluator, smart-retry, sub-agents}.ts`
-  - `context/{codebase-index, context-manager-v3, simple-vector-store,
-    sqlite-memory, summarizer}.ts` and `context/v3/*`
-  - `kernel/{hooks, permissions, runtime}.ts`
-  - `llm/{models, thinking-engine}.ts`
-  - `mcp/{client, server}.ts`
-  - `planner/{classifier, executor, smart-planner-v2}.ts`
-  - `tools/{compact, glob, multi-edit, project-intelligence, registry-v3,
-    todo-manager, web-search, v2/web, v2/background}.ts`
-  - `repl/todo-renderer.ts`
-  - `templates/template-manager.ts`
-  - `types/{web-deps, xenova-transformers}.d.ts`
-- **~95 unused imports** across live files, removed via static analysis.
-- **Legacy `setOutputCallback` printer** in `loop.ts` — superseded by the
-  Theatre pipeline.
-- **Hardcoded `2.0.0` strings** — now bind dynamically to `package.json`.
-
-### Fixed
-- `api/server.ts` health endpoint returns the real version from `package.json`.
-- `team-conductor.ts` no longer holds an unused `config` field.
-- `loop.ts` `BACKUP_DIR` and unused `fsPromises` removed.
-- All `tsc --noUnusedLocals --noUnusedParameters` warnings cleared.
-
-### Hard Guarantees
-- ✅ `npm run build` (strict TS) passes with **zero** errors.
-- ✅ `npm test` passes (11/11 channel tests).
-- ✅ `npm install` succeeds with the declared dependencies (no phantom imports).
-- ✅ Hablas is the sole speaker to the user — no agent surprises.
-- ✅ Token budget capped per turn; silent fallback when LLM is offline.
-- ✅ Web app, Supabase schema, and `@Consul` collaboration code untouched.
-
-### Engineering Stats
-| Metric | Before | After |
-|---|---|---|
-| TypeScript files | 111 | **74** |
-| Total LOC | 27,143 | **~21,000** |
-| Dead-code files | 37 | **0** |
-| Unused imports/declarations | 103 | **0** |
-| `--noUnusedLocals` clean | ❌ | ✅ |
-| `--noUnusedParameters` clean | ❌ | ✅ |
-| `@ts-ignore` count | 0 | **0** |
-| Unit tests | 0 | **11** |
-
----
-
-> The full audit that drove this release is preserved in
-> [`AUDIT_v1.0.0.md`](./AUDIT_v1.0.0.md).
+- Hablas is now presented as a **single visible engineering agent**
+- the active CLI surface was rewritten from scratch
+- the terminal UI was rebuilt into a simpler minimal style
+- help, startup messaging, and docs were rewritten around the new product model
+
+### Removed from active stable branch
+- visible mode-era CLI surface
+- visible team-theatre runtime surface
+- specialist handoff UX
+- old runtime/planner product surface
+- old rebuild and migration documentation set
+- large sections of dead source code and unused dependencies
+
+### Release intent
+2.0.0 is the first explicit release candidate of the full stable-branch rebuild direction.

package/README.md

@@ -1,70 +1,29 @@
-<div align="center">
+# Hablas CLI
 
-# ◆ Hablas CLI
+**Single-agent terminal AI engineering runtime**.
 
-**Premium multi-agent AI coding agent for your terminal**
+Hablas is being rebuilt from scratch around one strict product decision:
 
-Local-first · Cloud-compatible · One command surface · Internal specialist coordination
+> one visible agent, one execution surface, full tools, zero internal theatre
 
-*by [Abdulmoin Hablas](https://portfolio-monopoly63s-projects.vercel.app/)*
-
-[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
-[![Version](https://img.shields.io/badge/version-1.3.21-gold.svg)](CHANGELOG.md)
-[![Node.js](https://img.shields.io/badge/Node.js-20%2B-green.svg)](https://nodejs.org)
-[![TypeScript](https://img.shields.io/badge/TypeScript-5.5-blue.svg)](https://www.typescriptlang.org)
-
-</div>
+This stable branch no longer treats multi-agent choreography as the product.
+The product is now **Hablas only**.
 
 ---
 
-## ✦ Overview
-
-**Hablas** is a terminal AI development system with a **single user-facing agent** and an **internal team of specialists**.
-
-You talk only to **Hablas**. Internally, Hablas can coordinate:
-- **Emma** for product framing and requirements
-- **Bob** for architecture and systems design
-- **Alex** for implementation and debugging
-- **David** for research and supporting analysis
-
-The current stable direction is intentionally simple:
-- no visible mode system
-- no hidden theatrical router persona
-- one unified runtime that decides, internally and honestly, between:
-  - **direct leader handling** for simple turns
-  - **coordinated team execution** for serious engineering work
-
-Hablas runs **locally via Ollama**, or against **any OpenAI-compatible API**
-including **NVIDIA NIM**, OpenAI, Groq, Together, OpenRouter, and others.
-
-### ✨ Stable-line principles
-
-- **Single command surface** — use `hablas` interactively or `hablas run "..."` non-interactively.
-- **Architectural honesty** — routing is internal runtime behavior, not a public mode maze.
-- **Leader-first UX** — the user speaks to Hablas only; specialists stay internal.
-- **Real execution paths** — direct turns use the main agentic loop; coordinated turns use the internal team.
-- **Continuity-aware** — unfinished project requests can stay on the team path and reuse context.
-- **One-step delivery support** — requests like “finished project, no questions” preserve a dedicated internal flag.
-
-### Key Features
-
-- **Unified Runtime** — one internal runtime decides `direct` vs `team` execution.
-- **Multi-Agent Coordination** — Hablas can internally orchestrate Emma, Bob, Alex, and David.
-- **Dual Provider** — Ollama (local), NVIDIA NIM, or any OpenAI-compatible API.
-- **Dynamic Model Discovery** — `/models` lists everything your provider exposes.
-- **Agentic Loop** — multi-step tool execution with retries, tool safety, and recovery hints.
-- **Built-in Tools** — file ops, shell, codebase search, web search, scraping, PDF reading, code execution, and more.
-- **Smart Context** — project-aware prompts, persistent memory, shared notebook, and file auto-injection.
-- **Premium TUI** — executive-silver terminal UI with team rendering and status components.
-- **Three-tier safety** — `safe / confirm / dangerous` tool policy behavior.
-- **Ctrl+C UX** — single press cancels the current op, double press exits cleanly.
-- **Auto Mode** — `--auto` skips tool confirmations when appropriate.
-- **Checkpoints & Undo** — `/checkpoint ...`, `/undo ...`.
-- **Team Mode** — optional Supabase + Git-based locks and presence sync.
+## Product principles
+
+1. **Single visible agent**
+2. **Fast direct path for trivial turns**
+3. **Full tool execution for real engineering work**
+4. **No hidden routing leaks in the UX**
+5. **No handoff theatre, no mode maze, no orchestration drama**
+6. **Read before edit, verify before claim**
+7. **Direct technical tone: no emojis, no hype, no filler**
 
 ---
 
-## ✦ Installation
+## Installation
 
 ```bash
 git clone https://github.com/Monopoly63/mobile-bot.git
@@ -74,289 +33,160 @@ npm run build
 npm link
 ```
 
-### Requirements
+Requirements:
+- Node.js 20+
+- One provider:
+  - Ollama
+  - NVIDIA NIM
+  - any OpenAI-compatible API
 
-- **Node.js 20+**
-- One of:
-  - **Ollama** running locally (`ollama serve`)
-  - An **OpenAI-compatible API** key
-  - **NVIDIA NIM** API key
+---
 
-First run launches a setup wizard. You can re-run it anytime with:
+## Usage
+
+### Interactive
 
 ```bash
-hablas --setup
+hablas
 ```
 
----
-
-## ✦ Quick Start
+### Interactive with automatic tool confirmations where allowed
 
 ```bash
-# Interactive REPL
-hablas
-
-# Interactive REPL with auto-confirm for tools
 hablas --auto
-
-# One-shot unified runtime execution
-hablas run "refactor src/auth.ts to use bcrypt"
-
-# Generate a commit message from staged changes
-hablas commit
-
-# Project info
-hablas info
-
-# Diagnostics
-hablas doctor
 ```
 
----
-
-## ✦ Mental Model
-
-Hablas no longer exposes public modes like `build`, `design`, or `ask`.
-
-Instead, every request goes through one internal runtime:
-
-1. **User input**
-2. **Unified runtime routing**
-3. **Direct leader path** *or* **coordinated team path**
-4. **Final answer from Hablas**
-
-Examples:
-
-- `hi` → direct reply
-- `what is the current version of this project?` → direct reply
-- `design the architecture for auth` → team analysis path
-- `continue the unfinished flower store project` → team continuity path
-- `just give me the finished project in one step no questions` → team one-step delivery path
+### One-shot
 
----
-
-## ✦ Commands Reference
-
-### Core Slash Commands
-
-| Command | Description |
-|---|---|
-| `/help` | List all commands |
-| `/about` · `/version` | Identity & version info |
-| `/team` · `/agents` | Team roster · multi-agent system status |
-| `/agents on\|off\|status\|models` | Toggle and inspect agents |
-| `/delegate <agent> <task>` | Manually assign a task to one visible specialist |
-| `/mindset <name>` · `/mindsets` | Switch / list agent mindsets |
-| `/clear` · `/history [n]` | Reset context · show recent turns |
-| `/status` · `/quit` | Show status · exit |
-
-### Model & Provider
-
-| Command | Description |
-|---|---|
-| `/model [name]` | Show or switch the active model |
-| `/models [page\|query]` | Browse available models |
-| `/provider [ollama\|nvidia\|custom\|test]` | Switch / test the provider |
-| `/addmodel` · `/listmodels` · `/usemodel <name>` · `/removemodel <name>` | Manage saved provider profiles |
-
-### Project Tools
-
-| Command | Description |
-|---|---|
-| `/security` | Run the project security scan |
-| `/git status` | Show Git status |
-| `/workspace` | Show framework/language/CI detection |
-| `/stats` · `/cost` | Usage analytics |
-| `/test [--fix]` | Detect & run tests, optionally let the agent fix them |
-| `/checkpoint save\|list\|restore\|delete` | Snapshot & restore project state |
-| `/undo [N\|all\|list]` | Revert recent agent changes |
-| `/compare <a> <b>` · `/compare HEAD~1` | Side-by-side diff |
-
-### Memory & Context
-
-| Command | Description |
-|---|---|
-| `/memory [set\|del\|search\|clear]` | Persistent project memory |
-| `/learn "<preference>"` | Teach the agent a preference |
-| `/context [set\|get\|del\|decisions\|clear]` | Cross-agent shared notebook |
-| `/plan status\|finish\|next\|reset` | Inspect the active plan state if one exists |
-
-### Plugins & Diagnostics
-
-| Command | Description |
-|---|---|
-| `/plugins [enable\|disable]` | Manage plugins (`~/.hablas/plugins/`) |
-| `/alias [set\|del]` | Custom command aliases |
-| `/doctor` | System diagnostics |
-| `/session save\|list\|load` | Save/load conversation state |
-
----
-
-## ✦ CLI Flags & Sub-commands
-
-| Flag / Sub-command | Description |
-|---|---|
-| `-m, --model <name>` | Set the active model |
-| `-p, --project <path>` | Set the working directory |
-| `--provider <ollama\|custom\|nvidia>` | Choose LLM provider |
-| `--api-url <url>` · `--api-key <key>` | Configure custom/NVIDIA provider |
-| `--auto` | Skip tool confirmations where allowed |
-| `--timeout <ms>` | Per-request timeout (default 120000) |
-| `--theme <dark\|light\|galaxy\|ocean\|forest>` | UI theme |
-| `--team --user <name> --team-key <pwd>` | Enable Team Mode |
-| `--setup` | Run the first-time wizard |
-| `hablas run "<prompt>"` | Non-interactive unified runtime execution |
-| `hablas commit` · `pr` · `changelog` | Git intelligence sub-commands |
-| `hablas info` · `doctor` · `security` · `stats` | Project insights |
-| `hablas api --port 8080` | Start the REST API server |
+```bash
+hablas run "read package.json and tell me the version"
+```
 
 ---
 
-## ✦ Built-in Tools
-
-| Tool | Purpose | Safety |
-|---|---|---|
-| `read_file`, `list_dir`, `get_file_info` | Read filesystem | safe |
-| `write_file`, `edit_file`, `patch_file`, `append_to_file`, `search_and_replace` | Mutate files | confirm |
-| `delete_file`, `move_file`, `create_dir` | Manage paths | dangerous / confirm |
-| `run_command` | Shell execution (timeout + blocklist) | dangerous |
-| `search_codebase` | Codebase search | safe |
-| `detect_bugs` | Static analysis | safe |
-| `web_search` | Web search | safe |
-| `scrape_url`, `extract_links` | HTML scraping | safe |
-| `read_pdf`, `pdf_metadata` | PDF reading | safe |
-| `execute_code` | Sandboxed code execution | confirm |
+## Current command surface
+
+### CLI commands
+- `hablas`
+- `hablas run "..."`
+- `hablas doctor`
+- `hablas info`
+- `hablas security`
+- `hablas stats`
+- `hablas --setup`
+
+### Slash commands
+- `/help`
+- `/status`
+- `/model [name]`
+- `/models [query]`
+- `/provider [ollama|nvidia|custom|test]`
+- `/history [n]`
+- `/clear`
+- `/workspace`
+- `/doctor`
+- `/version`
+- `/about`
+- `/exit`
 
 ---
 
-## ✦ Configuration
-
-Config lives at **`~/.hablas/config.json`**.
+## Execution model
 
-| File | Purpose |
-|---|---|
-| `~/.hablas/config.json` | Main config (model, provider, theme, flags) |
-| `~/.hablas/agent-models.json` | Per-agent model overrides |
-| `~/.hablas/models.json` | Saved provider profiles (`/addmodel`) |
-| `~/.hablas/aliases.json` | Custom slash-command aliases |
-| `~/.hablas/memory/<hash>.json` | Per-project memory store |
-| `~/.hablas/plugins/` | Installed plugins |
-| `~/.hablas/logs/` | Structured pino logs |
-
----
+Hablas analyzes a request into one of four internal task kinds:
+- `casual`
+- `read`
+- `analysis`
+- `implementation`
 
-## ✦ The Internal Team
+Then it decides whether the turn should be:
+- **direct text execution**
+- **tool-based execution**
 
-| Agent | Title | Primary Responsibility |
-|---|---|---|
-| **★ Hablas** | Team Leader | User interface, routing, synthesis, final delivery |
-| **◆ Emma** | Product Manager | Requirements, framing, PRDs, scope |
-| **◆ Bob** | Architect | Architecture, structure, trade-offs |
-| **◆ Alex** | Engineer | Implementation, debugging, code changes |
-| **◆ David** | Data Analyst | Research, comparisons, supporting analysis |
-
-The user speaks to **Hablas only**.
-The rest of the team is an internal execution system.
+There is no public `build/design/ask` mode system anymore.
+There is no visible team routing layer.
 
 ---
 
-## ✦ Examples
-
-```bash
-# Read, then edit
-> read src/auth.ts and add JWT validation
+## Examples
 
-# Architecture-heavy request
-> design the architecture for a /users endpoint with tests and clear module boundaries
+### Simple direct turn
+```text
+hi
+```
+Expected behavior:
+- no tool calls
+- short direct answer
 
-# Continuity request
-> continue the unfinished flower store project from the previous PRD
+### Project inspection
+```text
+what is the current version of this project
+```
+Expected behavior:
+- inspect the minimum relevant files
+- answer from evidence
 
-# Specific visible specialist
-> /delegate bob design the cache layer for the search API
+### Architecture request
+```text
+design the architecture for auth in this repository
+```
+Expected behavior:
+- structured analysis
+- inspect files only if needed
+- answer as one agent
 
-# Git workflow
-> hablas commit
-> hablas pr --base main
-> hablas changelog --version 1.1.0
+### Continuation request
+```text
+continue the unfinished project
+```
+Expected behavior:
+- continue from existing work
+- do not restart from zero
 
-# Memory
-> /learn always use tabs and 2-space indent for YAML
-> /memory search auth
+### One-step delivery request
+```text
+just give me the finished project in one step no questions
 ```
+Expected behavior:
+- aggressive execution posture
+- no unnecessary follow-up questions
+- verify before claiming done
 
 ---
 
-## ✦ Architecture
+## Architecture docs
 
-```text
-src/
-├── repl/          REPL loop, slash commands, terminal rendering
-├── agents/        Agent runner, conductor, channel, shared execution engine
-├── runtime/       Unified router, contracts, planner, state, reviewer
-├── llm/           Unified provider layer (Ollama/Custom/NVIDIA)
-├── mindset/       Per-agent system prompts
-├── tools/         Tool registry + built-in tools
-├── context/       Session, memory, shared notebook, auto-inject
-├── config/        Defaults + JSON loader
-├── collaboration/ Optional Team Mode (Supabase + Git locks)
-├── plugins/       Plugin loader + diagnostics
-├── security/      /security scanner
-├── analytics/     Usage stats
-├── git/           /commit /pr /changelog intelligence
-├── workspace/     Framework / language / CI detection
-└── utils/         logger, diff, tokens
-```
-
-Stable-line architecture focus:
-- **one runtime entry**
-- **direct vs team execution path**
-- **single leader UX**
-- **no public mode system**
+See:
+- `docs/ARCHITECTURE.md`
+- `docs/CLI.md`
+- `docs/ROADMAP.md`
+- `docs/STATUS.md`
+- `docs/PUBLISH.md`
 
 ---
 
-## ✦ Development
+## Development
 
 ```bash
 npm install
 npm run build
-npm run lint
 npm test
 npm run dev -- run "your prompt"
 ```
 
-Current automated verification includes:
-- agent channel tests
-- execution parity tests
-- unified runtime routing regression tests
+Current automated checks cover:
+- shared execution engine smoke behavior
+- analyzer behavior
 
 ---
 
-## ✦ Documentation Notes
-
-Some older design documents in `docs/` describe intermediate runtime experiments
-such as visible modes or hidden gate-based routing.
-
-For the current stable direction, start with:
-- `docs/stable-runtime-recovery-plan-2026-06-12.md`
-
-Treat older redesign / migration docs as **historical context**, not as the
-current product surface.
-
----
-
-## ✦ Author
-
-**Abdulmoin Hablas** — [Portfolio](https://portfolio-monopoly63s-projects.vercel.app/)
-
-### Other Projects
+## Rebuild status
 
-- **mobile-bot** — the web companion + landing pages
-- **Hablas Web Chat** — ChatGPT-style chat on the web
+This branch is under an intentional **full rebuild** of the stable product surface.
+Dead code from the previous multi-agent product is being physically removed instead of patched.
 
 ---
 
-## ✦ License
+## License
 
-[MIT](LICENSE) © 2024-2026 Abdulmoin Hablas
+MIT