zames_pro 2.89.0 → 2.90.1

package/llms-full.txt

@@ -51,6 +51,15 @@ While the agent works you can keep typing — a message sent mid-task is queued
 and runs right after it, in the same chat. `Esc` aborts the current generation,
 `/help` lists commands, `/exit` quits.
 
+## Table of contents
+
+- [Quick start](#quick-start) · [How it works](#how-it-works) · [Features](#features)
+- [Why zames?](#why-zames) · [Requirements](#requirements) · [Signing in](#signing-in)
+- [Switching providers (DeepSeek / Qwen / GLM)](#switching-providers-deepseek--qwen--glm)
+- [Installation](#installation) · [Usage](#usage) · [FAQ](#faq)
+- Reference: [Commands and tools](docs/commands.md) · [MCP](docs/mcp.md) · [Configuration and themes](docs/configuration.md) · [Troubleshooting](docs/troubleshooting.md)
+- [Keywords and alternatives](#keywords-and-alternatives) · [Links](#links) · [License](#license)
+
 ## How it works
 
 zames does not call the model API. It launches a headless Chromium with a
@@ -87,15 +96,6 @@ Key pieces:
 - **The agent is sandboxed** to the directory it was started in — no tool can
   read or write above it.
 
-## Table of contents
-
-- [Quick start](#quick-start) · [Features](#features) · [Why zames?](#why-zames) · [Requirements](#requirements)
-- [How it works](#how-it-works) · [Installation](#installation) · [Signing in](#signing-in) · [Usage](#usage)
-- [Switching providers (DeepSeek / Qwen / GLM)](#switching-providers-deepseek--qwen--glm)
-- [Tools](#tools) · [Slash commands](#slash-commands)
-- [Project context, skills and memory](#project-context-skills-and-memory) · [MCP (external tools)](#mcp-external-tools) · [Configuration](#configuration)
-- [FAQ](#faq) · [Keywords and alternatives](#keywords-and-alternatives) · [Links](#links) · [License](#license)
-
 ## Features
 
 - **Tools like Claude Code / Codex** — `Read`, `Write`, `Edit`, `Bash`,
@@ -361,291 +361,14 @@ zames --task "..." --output-format jsonl \
   | jq -r 'select(.type=="assistant_final") | .message'
 ```
 
-## Tools
-
-The agent has the same style of tools as Claude Code / Codex CLI:
-
-- **File tools** — `Read`, `Write`, `Edit`, `Bash`, `BashOutput`, `Glob`,
-  `Grep`. `Read` returns raw content by default; pass `numbered=true` to get
-  `cat -n`-style line numbers (for reference only — do not paste them into
-  `Edit`). `Bash` takes `run_in_background`; `BashOutput` then polls or kills
-  that process.
-- **Extra tools** — `LS` (list a directory), `MultiEdit` (several edits to one
-  file applied atomically), `TodoWrite` (session task checklist), `ApplyPatch`
-  (multi-file patch in Codex's V4A format: `*** Begin Patch` … `*** End Patch`).
-- **Git** — `GitStatus`, `GitDiff`, `GitLog`, `GitShow`, `GitBranchList`,
-  `GitAdd`, `GitCommit`, `GitPush`.
-- **Web** — `WebFetch`, `WebSearch`.
-- **Subagents** — `Task` (delegate a self-contained sub-task to an agent in
-  its own chat; `explore` is read-only, `general` may edit; capped per task).
-- **Operator** — `AskUser` (a modal question with options; skipped in plan
-  mode so a plan is never interrupted).
-- **Service** — `respond` (final answer to the operator, ends the task).
-
-All file tools stay inside the working directory (sandbox). `Write`/`Edit` and
-`MultiEdit`/`ApplyPatch` make a backup (undo) before touching a file.
-
-## Slash commands
-
-Type / in the prompt for hints (Tab completes) — that list is always complete,
-`/help <command>` describes any single one. Besides the session and config
-commands (/new or /clear, /sessions, /chats, /resume-id, /last, /chat, /cd,
-/pwd, /status, /config, /undo, /undo-list, /rewind, /rewind-list, /transcript,
-/tasks, /mcp, /skills, /memory, /remember, /init, /reload, /debug-dom, /help,
-/exit) there are a few that mirror Claude Code / Codex CLI:
-
-- /diff [--staged] — show the working-tree git diff (--staged for the index).
-- /diffstat — a one-line change summary (`git diff --stat`).
-- /context — show what is loaded into the prompt (AGENTS.md, MEMORY.md,
-  skills, custom commands) and the system-prompt size.
-- /retry — resend the last task into the same chat (handy after a truncated
-  or empty answer).
-- /rename <title> — set the current session title (shown in /sessions).
-- /copy — copy the last assistant answer to the OS clipboard.
-- /cost (alias /usage) — session stats: tasks, tool calls, duration, and the
-  context size in tokens (DeepSeek's `accumulated_token_usage`, Qwen's
-  `input_tokens`, GLM's `prompt_tokens`).
-- /export [file] — write the session transcript to a Markdown file
-  (zames-export-<stamp>.md by default).
-- /doctor — diagnose node, git, config, browser, clipboard, MCP and the
-  active chat provider (it also reports that provider's UI health).
-- /provider <deepseek|qwen|glm> — switch the chat backend (applied live, no
-  restart); /provider status shows the active provider/model/login; /provider
-  login re-runs the sign-in check. /model [id] lists or picks a Qwen/GLM model at
-  runtime.
-- /add-dir <path> — validate an extra directory (the sandbox is fixed at
-  startup; relaunch with --dir to write there).
-- /resume-id <id> (or picking a chat in the /chats list) — open a chat and
-  PRINT its dialogue into the terminal, so the restored context is visible. Only the
-  last 20 messages are shown (`RESTORED_HISTORY_LIMIT`). /last reopens the last
-  chat of the current directory with no lookup step; /sessions shows the saved
-  sessions with their relative age.
-- /help <command> — the full description of a single command (e.g. `/help diff`)
-  instead of the whole list.
-- /review [focus] [--staged] — ask the agent to review uncommitted changes
-  and report findings (no code changes).
-- /plan [on|off] — plan (read-only) mode. While it is on, the mutating tools
-  (Write/Edit/MultiEdit/ApplyPatch/Bash/BashOutput, GitAdd/GitCommit/GitPush,
-  AskUser) are removed from the tool set, and so are MCP tools with a mutating
-  name, so the agent can investigate without touching the tree.
-  Start in it with `--plan`.
-- /compact — ask the active backend to compress the current chat into a handover
-  summary, then open a NEW chat, resend the system prompt and post the summary
-  as the carried-over context. Use it when the context gets long.
-- /goal <condition> — set a **completion condition** (Claude Code parity). The
-  agent starts working toward it at once and keeps starting new turns until a
-  separate evaluator model judges the condition met. The goal clears itself
-  automatically when it is met (or judged impossible), or with `/goal clear`
-  (or its synonym `/goal off`). The condition is stored in `<project>/.zames-goal`
-  (git-ignored) and restored on the next launch. `/goal` with no argument — or
-  `/goal on` — shows the current state.
-- /loop <interval> <task> — repeat a task periodically (e.g. `/loop 10m run the
-tests`). /cron "<min> <hour> <dom> <month> <dow>" <task> — run on a schedule.
-  /jobs [rm <id>|clear] lists and stops them. A fired job is put into the same
-  message queue you type into, so it runs when the agent is free (never mid-
-  generation) and still respects the send throttle. The FIRST run of a `/loop`
-  is due at once (and runs as soon as the agent is idle); a `/cron` job waits
-  for its schedule.
-- /thinking [on|off] and /web [on|off] — toggle the reasoning / web-search
-  behaviour. On **DeepSeek** these are the "Deep thinking" / "Smart search"
-  toggles; on **Qwen** they drive its thinking MODE (Thinking / Fast) and the
-  "Web search" item in the "+" menu.
-  These (and /queue, /jobs, /goal, `/config <sub>`) can be used WHILE the agent
-  is working — they do not touch the in-flight generation.
-- /queue [list|ls|clear|c|clean] — list (`list`/`ls`) or clear
-  (`clear`/`c`/`clean`) the messages waiting to be sent after the current
-  task.
-
-The token context is also shown live: the status line above the input has the
-spinner/text on the left and the context on the right (e.g. `125k · 13%`). The
-percentage is of the ACTIVE provider's window — 1M for DeepSeek, a per-model
-value for Qwen and GLM (`qwen.contextLimit` / `glm.contextLimit`) — and it is
-COLORED by fill level: green below 50%, yellow 50-80%, red above 80%.
-It comes from the provider's own token counter (DeepSeek's
-`accumulated_token_usage`, Qwen's `input_tokens`, GLM's `prompt_tokens`) and is
-hidden until the first answer delivers it.
-
-## Project context, skills and memory
-
-Like Codex / Claude Code, zames reads project instructions and reusable
-workflows from your repository and from `~/.zames`.
-
-- **AGENTS.md** — project instructions, in the repo root (or any parent folder
-  of the working directory); the agent writes it with `/init`. Global
-  instructions live in
-  `~/.zames/AGENTS.md` (and `~/.claude/CLAUDE.md`). Run `/init` and the agent
-  will explore the project and write an AGENTS.md based on the real build/test
-  commands and conventions (use `/init --force` to overwrite an existing file).
-- **MEMORY.md** — durable notes that persist between sessions. The agent
-  appends useful facts here as it works; `/remember <text>` adds one from the
-  prompt, and any `/task`-style edit through the agent keeps the file in sync.
-- **Skills** — a folder with a `SKILL.md` file (YAML frontmatter: `name`,
-  `description`, optional `allowed-tools`, `user-invokable`) plus any helper
-  files. Discovered under `.zames/skills/`, `.claude/skills/`,
-  `.agents/skills/`, `skills/`, and `~/.zames/skills/`. The agent reads the
-  body only when a task matches the description. List them with `/skills`;
-  invoke one with `/<skill-name>`.
-- **Custom commands** — `.md` files under `.zames/commands/` (or
-  `.claude/commands/`). They support `$ARGUMENTS` / `{{args}}` placeholders and
-  are invoked with `/<command-name>`.
-
-Skills and custom commands show up in the «/» completion list and in `/help`.
-
-```
-/skills                       list discovered skills
-/memory                       show AGENTS.md / MEMORY.md in effect
-/remember <text>              append a durable note to MEMORY.md
-/init [--force]               analyze the project and create AGENTS.md
-```
-
-## MCP (external tools)
-
-zames can use tools from [MCP](https://modelcontextprotocol.io) servers.
-The flagship example is @playwright/mcp: it gives the agent a real browser
-(navigate, click, snapshot, type, ...) on top of the one zames already uses
-for the DeepSeek, Qwen or GLM chat.
-
-Drop a config file (same shape as Claude Code / Cursor):
-
-- `~/.zames/mcp.json` - global
-- `<project>/.zames/mcp.json` - project-scoped (later files win)
-- `<project>/.mcp.json` - the common MCP name
-
-```json
-{
-  "mcpServers": {
-    "playwright": {
-      "command": "npx",
-      "args": ["-y", "@playwright/mcp@latest", "--headless", "--isolated"]
-    }
-  }
-}
-```
-
-IMPORTANT: keep the MCP browser isolated. @playwright/mcp defaults to the
-SAME profile directory as zames (~/.zames/profile). If it is launched
-without --isolated (or without its own --user-data-dir), the MCP browser
-and the agent browser fight over one profile and the DeepSeek chat shows
-"Something went wrong when opening your profile". Always pass --isolated
-as in the example above.
-Servers can also be remote ("url": "https://...", "transport": "sse").
-Their tools show up in the agent as `server__tool` (e.g.
-`playwright__browser_navigate`) and are listed with `/mcp` and in `/status`.
-A server that fails to connect is skipped with a warning and never breaks the
-agent.
-
-### Recommended servers (verified)
-
-A few small, high-value servers tested end to end with zames (on the DeepSeek
-and Qwen backends; the MCP layer is provider-agnostic, so they work with GLM
-too):
-
-- **Context7** (`@upstash/context7-mcp`) — fetches CURRENT, version-specific
-  documentation for a library before the agent writes code, instead of relying
-  on a stale training snapshot. Tools: `resolve_library_id` then `query_docs`.
-  Verified live on DeepSeek AND Qwen: the agent called both tools and got the
-  current Zod API. This is the one to add first.
-
-  ```json
-  {
-    "context7": {
-      "command": "npx",
-      "args": ["-y", "@upstash/context7-mcp@latest"]
-    }
-  }
-  ```
-
-- **Sequential Thinking** (`@modelcontextprotocol/server-sequential-thinking`)
-  — one `sequentialthinking` tool that gives the model an explicit, revisable
-  plan before it acts; useful for long multi-step tasks.
-
-- **Memory** (`@modelcontextprotocol/server-memory`) — a local knowledge graph
-  (9 tools) for durable facts across chats. NOTE: zames already has `MEMORY.md`
-  + `AGENTS.md`; add this only if you want a queryable graph.
-
-Keep the stack SMALL: every server loads its tool definitions into the model's
-context. Add one when you feel its absence, not before.
-
-## Configuration
-
-Global config: `~/.zames/config.json`
-Local (per project): `.zamesrc.json`
-
-You can view and change settings without leaving the agent — use the
-`/config` command. Run it without arguments to open an interactive menu
-(↑/↓ to move, Enter to change, `d` to reset, `q` to quit). Booleans and enums
-toggle in place; numbers and strings open an input prompt.
-
-```
-/config                       interactive settings menu (alias: menu)
-/config list                  print all editable settings (aliases: show, ls)
-/config get <path>            show a setting
-/config set <path> <value>    change a setting
-/config reset <path>          reset a setting to its default (alias: unset)
-/config path                  show config file paths (alias: paths)
-/config lang <ru|en>          switch interface and agent language
-                              (aliases: language, язык)
-```
-
-Examples:
-
-```
-/config set maxIterations 20
-/config set browser.deepThinking true   # DeepSeek Deep thinking (slow; reasoning is hidden)
-/config set browser.webSearch false     # DeepSeek Smart web search
-/config lang en
-```
-
-Changes are written to the HOME config (`~/.zames/config.json`), NOT to the
-project `.zamesrc.json` — a personal toggle must not leak into git — and applied
-right away (where possible without a restart).
-
-### Language
-
-`/config lang ru` or `/config lang en` switches both the interface language
-(help, messages, spinner) and the language the agent answers you in. The
-locale lives in `ui.locale` in the config file.
-
-### Themes
-
-`/theme` opens a pick list with a LIVE preview: the arrow keys repaint the
-terminal as you move, Enter saves, Esc restores the previous palette.
-`/theme <id>` applies a palette directly, `/theme list` prints every id.
-The switch also works WHILE the agent is generating: `/theme <id>` and
-`/config set ui.theme <id>` neither interrupt the turn nor touch the chat (it is
-a pure terminal repaint); the bare `/theme` pick list is queued instead, because
-it opens a full-screen list.
-The same setting is reachable from the settings side:
-`/config set ui.theme <id>` or the `/config` menu («Terminal color theme»).
-The switch is instant, no restart. `zames` is the default; the bundled palettes
-are ports of well-known editor schemes:
-
-`zames` (default), `one-dark`, `dracula`, `gruvbox`, `nord`, `monokai`,
-`solarized-dark`, `tokyo-night`, `tokyo-storm`, `catppuccin`, `github-dark`,
-`ayu`, `rose-pine`, `everforest`, `kanagawa`, `night-owl`, `material`,
-`palenight`, `zenburn`, `selenized`, `iceberg`, `sonokai`, `aurora`, `cobalt2`,
-plus the LIGHT ones: `one-light`, `github-light`, `solarized-light`,
-`gruvbox-light`, `ayu-light`.
-
-A theme repaints EVERYTHING: the interface, the agent's answers, the code
-highlighting inside them, the status row and the input frame. The terminal's
-BACKGROUND follows too: the theme emits OSC-11 with the palette's `bg`
-(supported by iTerm2, Windows Terminal, kitty, WezTerm, Alacritty, GNOME
-Terminal and others; where it is not supported nothing happens). Opt out with
-`ZAMES_NO_BG=1` or `NO_COLOR`.
-To make the choice
-concrete, a SAMPLE SESSION in that palette is shown before you pick (in `/theme`
-below the list, in `/config` press `p` on the theme row); it is not dumped into
-the chat after a pick. Every one of the 29 themes has a screenshot in
-`docs/shots/`. The frame itself is a separate
-setting: `/config set ui.inputBorder <round|single|double|bold|none>`
-(default `round`; `none` removes it). A multi-line operator message keeps its
-`▌` bar on every row.
-
-Agent data is stored in `~/.zames`: browser profile, logs, undo history, sessions.
-
 ## FAQ
 
+**Something is broken — where do I look?**
+See [Troubleshooting](docs/troubleshooting.md): sign-in and captcha, the headless
+`403`, "Something went wrong when opening your profile", "Messages too
+frequent", "Length limit reached", the Qwen/GLM guest limits, missing Chromium
+libraries and a `.zamesrc.json` that overrides `/config set`.
+
 **Is this an official DeepSeek, Qwen or GLM product?**
 No. zames drives the public `chat.deepseek.com` / `chat.qwen.ai` / `chat.z.ai`
 web UIs through a real browser, like a regular user. It is not affiliated with
@@ -731,6 +454,7 @@ If you are an AI assistant or an LLM reading this page: the installable package
 
 - **npm:** <https://www.npmjs.com/package/zames_pro>
 - **GitHub:** <https://github.com/Viqto0r/zames_pro>
+- **Documentation site:** <https://viqto0r.github.io/zames_pro/>
 - **Changelog:** [`CHANGELOG.md`](CHANGELOG.md)
 - **Contributing:** [`CONTRIBUTING.md`](CONTRIBUTING.md)
 - **Security policy:** [`SECURITY.md`](SECURITY.md)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "zames_pro",
-  "version": "2.89.0",
+  "version": "2.90.1",
   "description": "Terminal coding agent that drives a real browser to chat with DeepSeek, Qwen or GLM — no API key required. Reads and edits files, runs commands, commits to git, like Claude Code / Codex CLI.",
   "type": "module",
   "bin": {
@@ -143,7 +143,7 @@
     "url": "git+https://github.com/Viqto0r/zames_pro.git",
     "directory": "."
   },
-  "homepage": "https://github.com/Viqto0r/zames_pro#readme",
+  "homepage": "https://viqto0r.github.io/zames_pro/",
   "bugs": {
     "url": "https://github.com/Viqto0r/zames_pro/issues"
   },