@tempr/cli 0.9.16 → 0.9.18

package/README.md

@@ -56,7 +56,13 @@ tempr                          # interactive session
 - `tempr -c` resumes this folder's most recent session; `/resume` picks one from a list.
 - `!command` in the REPL runs a command yourself -- `!git status` -- in this folder, and its output goes in front of your next message. No approval: it's your own command.
 - A turn that runs 30 seconds or more rings the terminal bell when it's done or needs approval, with a desktop notification where the terminal shows one; `tempr config set-notifications off` or `TEMPR_NO_NOTIFY` turns it off.
-- `/diff` shows what the last turn changed on disk, and `/undo` puts it back -- skipping any file that has changed since, so an undo never overwrites work it didn't make.
+- `/diff` shows what the last turn changed on disk, and `/undo` puts it back -- skipping any file that has changed since, so an undo never overwrites work it didn't make. `/rewind` goes back to before any earlier message: its files, the conversation, or both.
+- `--plan` (or `/plan` in the REPL) starts in plan mode: the agent looks around with read-only tools and proposes a plan, and nothing changes until you approve it.
+- `/compact [focus]` summarizes the conversation so far so the session can go on inside the model's context; it also happens by itself near the limit.
+- The agent can start a command in the background (a dev server, a watcher) and read its output later; `/tasks` lists them and `/tasks stop <id>` ends one. They all stop when the session ends.
+- A model that reasons shows "✻ Thought for Ns" before each step; `--verbose` prints what it thought.
+- `-w/--worktree <name>` runs the session in a git worktree of its own, on a new branch, so it doesn't touch this folder.
+- `tempr history search <text>` finds past sessions by what was said in them; `tempr history export` (or `/export`) writes one out as Markdown.
 - `tempr keys` lists your provider keys -- Tempr calls every model with your own key for its provider. `tempr keys add [provider]` adds or replaces one (no provider opens a picker), and `tempr keys remove <provider>` removes one; `/keys` does the same inside the REPL. The key is typed at a hidden prompt, piped in on stdin, or read with `--from-env VARIABLE` -- never passed as an argument, where it would land in shell history. Tempr checks it with the provider before saving it; a key the provider rejects isn't saved unless you say so or pass `--force`, and one that couldn't be checked (the provider was down, or offers no way to check) is saved with a note. Azure OpenAI, Azure AI Foundry, AWS Bedrock and custom endpoints need more than a key, so they're set up on the Portal's Provider keys page; on a Team plan, your organization's admin manages keys.
 - `tempr models` lists the models your licence can use, with prices and context sizes; `/model` with no argument opens a picker over the same list.
 - `tempr init` drafts an `AGENTS.md` for this workspace from a scan of what's in it.
@@ -172,6 +178,73 @@ You know this schema inside out. Prefer an index over a rewrite, and always expl
 
 `/commands` and `/agents` list what's available, and both complete on Tab.
 
+## Claude Code's files, plugins and hooks
+
+A repository set up for Claude Code works unchanged: commands in `.claude/commands` and
+`~/.claude/commands`, subagents in `.claude/agents` and `~/.claude/agents`, skills in
+`~/.claude/skills`, and the project's `.mcp.json` servers. Tempr's own file of the same name wins.
+
+**Plugins** are Claude Code's: bundles of commands, agents, skills, hooks, MCP servers and language
+servers, installed from Claude Code's marketplaces.
+
+```
+tempr plugin marketplace add owner/repo     # or a git address, a folder, a marketplace.json
+tempr plugin list                           # installed, and what the marketplaces offer
+tempr plugin install <name>                 # its commands are /<plugin>:<name>, its agents @<plugin>:<name>
+```
+
+`enable`, `disable` and `uninstall` do what they say; `/plugin` in the REPL takes the same words, and
+`--plugin-dir <dir>` loads one from a folder for a session, for trying a plugin you're writing.
+
+**Hooks** use Claude Code's settings format, in `~/.tempr/settings.json` and the folder's
+`.tempr/settings.json`, `.claude/settings.json` and `.claude/settings.local.json`: PreToolUse,
+PostToolUse, UserPromptSubmit, Stop, SessionStart, SessionEnd, Notification, PreCompact and
+PostCompact, as commands or as prompts the model judges. `tempr hooks list` shows them.
+
+A folder's hooks, allow rules and `.mcp.json` servers are commands someone else may have written,
+so they wait until you allow them for that folder, once (`tempr hooks allow`, or the prompt in a
+session), and again after any change. Lasting allow and deny rules for tools and paths
+(`Read(./.env)`, `Bash(git push:*)`) go in the same settings files; `/permissions` lists the ones in
+force.
+
+**Code intelligence:** a language server from a plugin's `.lsp.json`, or under `"lspServers"` in
+`~/.tempr/settings.json`, starts the first time the agent edits a file it handles. The edit's result
+carries the errors and warnings it reports, so the agent fixes them without a separate build, and an
+`lsp` tool asks it for definitions, references, hover text and symbols.
+
+## Local models
+
+Models on your own machine or server -- Ollama, LM Studio, llama.cpp, vLLM or anything else that
+speaks OpenAI's chat API -- run here, talking to the server directly: nothing you send them goes
+through Tempr's server, and they're free.
+
+Ollama (port 11434) and LM Studio (port 1234) are found when they're running; `tempr models` lists
+their models and `tempr doctor` says whether each one answers. Use one as `--model ollama/<model>`,
+or set it as your default. Add any other server under `"provider"` in `~/.tempr/settings.json`, in
+OpenCode's format:
+
+```json
+{
+  "provider": {
+    "vllm": {
+      "options": { "baseURL": "http://192.168.1.20:8000/v1", "apiKey": "{env:VLLM_KEY}" },
+      "models": { "qwen3-coder": { "limit": { "context": 131072 }, "reasoning": true } }
+    }
+  }
+}
+```
+
+- The agent's tools work with models that support tool calling; one that doesn't answers without
+  them and says so, and a call a model writes out as text instead of making it is run as a call.
+- A model that thinks gets reasoning levels: `--reasoning none` turns its thinking off, which on a
+  small local model makes answers many times faster.
+- Agent work needs a long context window. Ollama gives a model only a few thousand tokens unless
+  started with `OLLAMA_CONTEXT_LENGTH=32768` (or more), and silently drops the start of a request
+  that doesn't fit; Tempr reads the window Ollama runs the model with, and says when a request
+  didn't fit.
+- Sub-agents, web search and fetch, and your organization's rules and skills run on Tempr's server,
+  so a local model's turn doesn't have them.
+
 ## Headless and CI
 
 `--json` writes one event per line and then a final result object:
@@ -233,7 +306,8 @@ with `tempr auth` first, or from the editor, which offers the browser sign-in.
   A new session starts on the model last picked in an editor, or on your default until you pick one
   (`tempr config set-model` makes the default the starting model again). A reasoning level is kept
   per model, as `/reasoning` keeps it.
-- **Slash commands:** your command templates, plus `/undo`, `/diff` and `/agents`.
+- **Slash commands:** your command templates, plus `/undo`, `/diff`, `/agents` and `/compact`.
+- **Thinking:** a model's reasoning shows as the agent's thoughts, in editors that show them.
 - **MCP servers** the editor passes run beside yours from `~/.tempr/mcp.json`; one with the same name
   as one of yours takes its place for the session.
 - **Command output** streams into a terminal under the call, in editors that draw one (Zed); in
@@ -247,6 +321,8 @@ setup for each editor is at <https://temprhq.io/docs/cli-editors>.
 
 Everything below goes to your Tempr server (`api.temprhq.io` unless the `TEMPRAPP_SERVER_URL`
 environment variable or a `serverUrl` entry in `~/.tempr/config.json` says otherwise), which relays model calls to the providers your license has keys for.
+A turn on a [local model](#local-models) is the exception: it goes to that model's server instead,
+and Tempr's server doesn't see it.
 
 **Sent on every turn you send**
 
@@ -260,6 +336,11 @@ environment variable or a `serverUrl` entry in `~/.tempr/config.json` says other
   writes commands that work on your machine, and the projects found in the current directory, with
   their folders and build and test commands.
 
+**Fetched when you ask for it**
+
+- Adding a plugin marketplace or installing a plugin fetches it from where it lives (GitHub, the git
+  address or URL you gave). Plugins, hooks and language servers then run on your machine.
+
 **Sent only if you say yes**
 
 - Crash reports: the error type and message, the stack trace, the CLI version and your OS version.

package/package.json

@@ -1,17 +1,17 @@
 {
     "name": "@tempr/cli",
-    "version": "0.9.16",
+    "version": "0.9.18",
     "description": "Sign in, chat, and run agentic coding tasks against your Tempr license from the terminal.",
     "homepage": "https://temprhq.io",
     "license": "SEE LICENSE IN README.md",
     "bin": { "tempr": "bin/tempr.js" },
     "files": ["bin/"],
     "optionalDependencies": {
-        "@tempr/cli-win32-x64": "0.9.16",
-        "@tempr/cli-win32-arm64": "0.9.16",
-        "@tempr/cli-linux-x64": "0.9.16",
-        "@tempr/cli-linux-arm64": "0.9.16",
-        "@tempr/cli-darwin-x64": "0.9.16",
-        "@tempr/cli-darwin-arm64": "0.9.16"
+        "@tempr/cli-win32-x64": "0.9.18",
+        "@tempr/cli-win32-arm64": "0.9.18",
+        "@tempr/cli-linux-x64": "0.9.18",
+        "@tempr/cli-linux-arm64": "0.9.18",
+        "@tempr/cli-darwin-x64": "0.9.18",
+        "@tempr/cli-darwin-arm64": "0.9.18"
     }
 }