orka-cli 1.0.1 → 1.0.2

package/README.md

@@ -25,9 +25,6 @@ $ orka run "build user authentication with OAuth2 and JWT"
 - **Parallel multi-agent swarm** — Coordinator + Scout + N Builders + Reviewer work concurrently
 - **Zero file conflicts** — atomic SQLite file ownership locks prevent two agents from editing the same file
 - **AI self-healing loop** — TesterAgent runs your test suite after each build; if tests fail, Builder retries with the test output as feedback
-- **Human gate** — optionally require human approval before any task is marked done, with a full diff preview
-- **Web dashboard** — built-in HTTP server with real-time WebSocket updates; monitor and control sessions from any browser
-- **Remote access** — built-in Cloudflare Tunnel support (`--tunnel`) for iPad/remote access without VPN
 - **Provider-agnostic** — Claude, OpenAI, Gemini, Ollama (local/free), OpenRouter — mix and match per role
 - **Git integration** — auto-branch per session, auto-commit after approval, safe rollback
 - **Crash recovery** — full state persisted in SQLite; `orka resume` picks up exactly where it left off
@@ -57,31 +54,6 @@ orka login --provider claude
 orka run "add input validation to all API endpoints"
 ```
 
-## Web Dashboard (Mission Control)
-
-Run Orka as a persistent server and control everything from your browser — no terminal needed after startup.
-
-```bash
-# Start the server (point --static to the GUI build)
-orka serve --project /path/to/your-project --static /path/to/gui/dist
-
-# With Cloudflare Tunnel for iPad/remote access
-orka serve --project /path/to/your-project --static /path/to/gui/dist --tunnel
-# → 🌐 Tunnel URL: https://xxxxx.trycloudflare.com
-```
-
-From the dashboard you can:
-- **Start new sessions** — type a goal and click Run
-- **Monitor agents** — real-time swarm canvas with task status
-- **Review diffs** — click any `AWAITING APPROVAL` task to see the full git diff
-- **Approve or reject** — with optional feedback sent back to the Builder
-
-Alternatively, run server + session together in one command:
-
-```bash
-orka run "your goal" --serve --serve-static /path/to/gui/dist [--tunnel]
-```
-
 ## Configuration
 
 `orka init` generates `orka.config.yaml` in your project root:
@@ -97,7 +69,6 @@ swarm:
   builders: 2                         # number of parallel Builder agents
   review: true                        # enable Reviewer agent
   maxReviewRetries: 3
-  humanGate: false                    # set true to require human approval before done
 
 roles:
   coordinator: { provider: claude, model: claude-sonnet-4-20250514 }
@@ -139,22 +110,6 @@ roles:
   reviewer:    { provider: claude, model: claude-sonnet-4-20250514 }
 ```
 
-## Human Gate (Approval Workflow)
-
-Enable `humanGate: true` in your config to require human review before any task is finalized.
-
-**Pipeline with human gate:**
-```
-Builder → TesterAgent → ReviewerAgent → awaiting_approval → [you approve] → done
-                                                           ↘ [you reject]  → Builder retries
-```
-
-When a task reaches `awaiting_approval`:
-- The web dashboard shows a purple **APPROVE** badge
-- Click the task to open a diff preview modal
-- Click **Approve** to finalize, or **Reject** with optional feedback
-- On rejection, the Builder retries with your feedback as context
-
 ## Self-Healing Test Loop
 
 Enable `tester.enabled: true` to have Orka automatically run your test suite after each build:
@@ -202,8 +157,6 @@ orka run "goal" --builders 4             # use 4 parallel Builder agents
 orka run "goal" --provider claude        # override all roles to one provider
 orka run "goal" --dry-run                # preview plan without calling any LLM
 orka run "goal" --mock                   # use mock provider (no API calls, for testing)
-orka run "goal" --serve                  # start HTTP server alongside the session
-orka run "goal" --serve --tunnel         # + expose via Cloudflare Tunnel
 orka pause                               # pause all agents gracefully
 orka resume                              # resume from pause or crash
 orka rollback                            # rollback last session branch to base commit
@@ -221,15 +174,6 @@ orka logs --type task:completed          # filter by message type
 orka cost                                # show token usage and cost summary
 ```
 
-### Web Server
-```bash
-orka serve                               # start HTTP server + web dashboard
-orka serve --port 8080                   # custom port (default: 4242)
-orka serve --project /path/to/project   # set project directory
-orka serve --static /path/to/gui/dist   # serve web dashboard
-orka serve --tunnel                      # expose via Cloudflare Tunnel
-```
-
 ### Provider & Credentials
 ```bash
 orka login --provider claude             # save Claude API key
@@ -300,14 +244,14 @@ After all tasks are approved, Orka auto-commits to the session branch. You decid
 
 ## Supported Providers
 
-| Provider | Models | Notes |
-|----------|--------|-------|
-| **Claude** | claude-sonnet-4, claude-haiku-4-5, ... | Best quality |
-| **OpenAI** | gpt-4o, gpt-4o-mini, o1, ... | |
-| **Gemini** | gemini-2.0-flash, gemini-1.5-pro, ... | |
-| **Ollama** | llama3, deepseek-coder-v2, qwen2.5-coder, ... | Free, runs locally |
-| **OpenRouter** | Any model via OpenRouter | |
-| **Zai / GLM** | glm-4, ... | |
+| Provider | Notes |
+|----------|-------|
+| **Claude** | Best quality for planning and review |
+| **OpenAI** | GPT-4o, o1, and variants |
+| **Gemini** | Gemini 2.0 Flash, 1.5 Pro |
+| **Ollama** | Free, runs locally — llama3, deepseek-coder-v2, qwen2.5-coder |
+| **OpenRouter** | Access any model via OpenRouter |
+| **Zai / GLM** | GLM-4 and variants |
 
 ## MCP Integration
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "orka-cli",
-  "version": "1.0.1",
+  "version": "1.0.2",
   "description": "Multi-agent orchestration CLI",
   "type": "module",
   "bin": {