@wular/coder 0.1.16 → 0.1.18

package/README.md

@@ -6,7 +6,7 @@
 
 </div>
 
-One runtime that hands your coding tasks to the best engine available and lets you steer, inspect, or stop any job while it works.
+One runtime that hands your coding tasks to the best engine available and lets you steer, inspect, or stop any task while it works.
 
 Plugs into Claude Code or Codex to enable the harness with Coder instances.
 
@@ -15,11 +15,15 @@ Plugs into Claude Code or Codex to enable the harness with Coder instances.
 - **A clean main thread.** Installed in Claude Code or Codex, dispatch is a single command from your session; the actual coding runs in a Coder subagent. File dumps, test output, and retries stay there; only the outcome returns to your conversation.
 - **Fast dispatch.** Coder keeps a single Codex engine warm in the background and hands tasks to it directly, instead of booting the CLI for every request. A handoff starts in seconds.
 - **Unified permissions.** One permission model across agents, with three modes: **Read-only**, **Workspace-write**, and **Auto**. Auto is the default: safe commands run, dangerous ones are blocked, and anything in between is brought to you for a yes/no.
-- **Jobs you can steer.** Every task is a job. Check on it, read its result, give it follow-up instructions, or stop it, all by id, while it keeps working in the background.
+- **Tasks you can steer.** Every dispatch is a task. Check on it, read its result, give it follow-up instructions, or stop it, all by id, while it keeps working in the background.
 - **Graceful fallback.** If Codex can't start (auth, usage limits, not installed), the task flows to a Claude subagent with the same instructions. You configure the chain and the default model and effort for each agent.
+- **Any model, anywhere.** Codex can point at local models (Ollama, LM Studio, and other OpenAI-compatible endpoints) and third-party providers, so Coder can run your tasks on those too - not just the hosted defaults. That opens up the whole scope of engines you can delegate to.
 
 ## Get started
 
+Coder runs your tasks on an **engine CLI** - it needs at least one of the [codex CLI](https://github.com/openai/codex) (`npm install -g @openai/codex`, then `codex login`) or the [Claude Code CLI](https://github.com/anthropics/claude-code) (`npm install -g @anthropic-ai/claude-code`, then `claude auth login`) installed and logged in. `coder host-setup` reports which are ready; if none is, install one of them to run tasks.
+
+
 ### Claude Code
 
 ```
@@ -36,7 +40,7 @@ Or from the shell:
 
 ```
 npm install -g @wular/coder
-coder setup --claude
+coder host-setup --claude
 ```
 
 Then you can ask like:
@@ -60,7 +64,7 @@ Or from the npm directly:
 
 ```
 npm install -g @wular/coder
-coder setup --codex
+coder host-setup --codex
 ```
 
 Then ask like:
@@ -95,24 +99,20 @@ Machine defaults live in `~/.coder/config.json`; drop a `coder.config.json` in a
 
 ## Advanced usage
 
-You rarely need these: the agent creates and controls jobs on its own. But you can ask it explicitly ("steer that job", "approve that command", "stop it"), or run the commands yourself:
+You rarely need these - the agent drives tasks itself - but you can run them. Task commands live under `coder task <sub>`; the common ones have a top-level shortcut. Full docs: `coder --help`, `coder task <sub> --help`.
 
 ```bash
-coder task "<text>"              # run a task in the background (--wait to block)
-coder status [job]               # progress and pending approvals
-coder result [job]               # the final answer
-coder steer <job> "<follow-up>"  # continue a job with new instructions
-coder stop <job>                 # interrupt it
-coder approve <job> <id>         # answer an escalated permission (--deny)
+coder run "<text>"                # dispatch a task (--wait to block for the answer)
+coder result [task-id]            # status + final answer (--wait blocks until done)
+coder list [--all|--stopped]      # list tasks (running by default)
+coder task steer <id> "<text>"    # continue a task with new instructions
+coder task stop <id>              # interrupt it
+coder task stream [id]            # watch the live progress log (you/debugging)
+coder task archive <id>           # archive a session (--all-stopped for all finished)
+coder task delete <id>            # delete a session (--all-archived for all archived)
+coder task approve <id> <appr>    # answer an escalated permission (--deny)
 ```
 
-Common flags:
+`run`/`list`/`result`/`stream` are shortcuts for the `task` subcommand. Any `[task-id]` defaults to the most recent task and accepts a unique prefix.
 
-| Flag               | Values                                                                    | Default           |
-| ------------------ | ------------------------------------------------------------------------- | ----------------- |
-| `--wait`         | run in the foreground and print the answer                                | background        |
-| `--agent`        | `codex`, `claude`                                                     | first in`chain` |
-| `--model`        | `spark`, `luna`, `terra`, `sol`, `opus`, `sonnet`, `fable` or any raw model slug | from config       |
-| `--effort`       | `low`, `medium`, `high`                                             | from config       |
-| `--permissions`  | `read-only`, `workspace-write`, `auto`                              | `auto`          |
-| `--resume <job>` | continue that job's thread instead of starting fresh                      | fresh run         |
+Run flags (`run`/`steer`): `--wait` (foreground), `--agent codex|claude`, `--model spark|luna|terra|sol|opus|sonnet|fable`, `--effort low|medium|high`, `--permissions read-only|workspace-write|auto`, `--resume <task-id>`, `--json`.