Commit Graph
12 Commits
Author SHA1 Message Date
WHC 6e81513e36 v0.7.8: WebUI (--web): HTTP/1.1 + SSE front end, engine API v1, tests
A second implementation of cst_agent_hooks_t next to the TUI: the turn runs on
a worker thread, the hooks publish events into a ring buffer that SSE clients
read, so the engine itself needs no changes.

- src/net.c, include/cst_net.h: POSIX/Winsock sockets, non-blocking connect
- src/http_srv.c, include/cst_http.h: HTTP/1.1, keep-alive, chunked streaming,
  body caps (413), Expect: 100-continue, connection cap, exact routing
- src/web_md.c, include/cst_web_md.h: streaming markdown -> sanitized HTML
  (tag/attribute allowlist, javascript: URLs and off-site images dropped)
- src/webui.c, include/cst_webui.h: event ring + SSE broadcast, all routes,
  token (Bearer/Cookie/query) and loopback Host checks, 3 s auto-deny when no
  client is attached
- src/webui_stub.c, CST_WEBUI=0 / CST_BUILD_WEBUI=OFF: build without the WebUI
- web/: no-build front end (transcript, approvals, todo, sessions, image
  upload, status bar)
- docs/webui.md: engine API v1 - events, requests, security model
- tests/test_webui.c, scripts/e2e_webui.sh: unit tests plus an end-to-end run
  driven by a recorded SSE stream (no API key needed)
- src/main.c: --web --web-port --web-host --web-token --web-dev --web-open
  and CST_WEB_PORT/HOST/TOKEN/ROOT

An empty POST body is now accepted without Content-Length (RFC 9112 6.3) so
curl-driven clients can reach cancel/undo/compact/quit; CMakeList's core tests
learned about sashidown and test_webui, and CST_WEBUI=0 defines CST_NO_WEBUI.
2026-10-09 10:20:09 +08:00
WHC 895b47274c v0.7.0: image input, model registry, prefix-cache savings
Images
- vision gate: text-only models get a note instead of image parts and no
  view_image tool; unknown models retry once without images on HTTP 400
- paste: Ctrl+V and /attach paste read the clipboard (wl-paste, xclip,
  pngpaste/osascript, Win32 PNG or CF_DIB converted to PNG); pasting image
  file paths attaches them
- MCP image content is stored in the session and sent with the tool result
- attach: rel path validation, base64 decode, /retry keeps images

Model registry
- built-in src/models_builtin.json embedded at build time, merged with
  <config>/models.json and cached GET /models metadata (context, vision,
  pricing); most specific rule wins per field
- /model labels, /status source, --list-models [provider]

Cache and cost
- stable request prefix (frozen tools, notes as messages), DeepSeek prefix
  completion, OpenAI/Anthropic cache hints, /cost and hit rate in the status
2026-10-08 20:34:09 +08:00
WHC 630e8f4295 ci: Windows zip only builds cst-agent; link util for replay tests
os_win.c needs cst_buf_* / cst_utf8_valid from util.c after os_compat was
added to the small replay CMake targets. Release packaging only needs
cst-agent.exe, so bootstrap_windows.sh builds that target alone.
2026-10-07 21:09:44 +08:00
WHC 546a4c7eeb ci: link os_compat for replay CMake tests; fix llvm-mingw mirrors
gcc -O0 keeps unused cst_test_util.h helpers that need os_*; clang GC'd
them so only the gcc CMake step failed. Prefer ghfast/ghproxy.net for the
llvm-mingw tarball (gitclone 500 / github unreachable on the runner).
2026-10-07 02:57:38 +08:00
WHC 1476f1774a Temp dir falls back when TMPDIR or /tmp is unusable (Termux); v0.6.1
os_temp_dir() used $TMPDIR or "/tmp" without checking either. On Termux
/tmp usually does not exist (or SELinux denies it) unless TMPDIR points at
$PREFIX/tmp, so plugin and MCP temp files failed and shell children that
need a temp file (heredocs) broke.

  * os_temp_dir() picks, once, the first of $TMPDIR, $PREFIX/tmp, /tmp,
    /var/tmp and ~/.cache/cst-agent/tmp where a file can really be
    created; if none works it keeps the old answer
  * os_temp_dir_export() at startup writes the choice back to TMPDIR, so
    shell children and the sandbox's writable temp dir agree
  * tests/test_tmpdir.c covers the fallbacks in fresh forks
2026-10-06 23:32:21 +08:00
WHC 2a43ae6622 Windows: official port -- UCRT static build, UTF-8 throughout, Low IL sandbox, ncurses TUI, installer; v0.6.0
Build
  * cross build switches to pkgsCross.ucrt64 (shell-win.nix); curl (Schannel),
    winpthreads and ncurses 6.6 are linked statically, so the release is
    cst-agent.exe + busybox.exe (busybox-w32 Unicode) with no extra DLLs
  * windres embeds a manifest with activeCodePage=UTF-8 and a version resource
  * ncurses 6.6 Windows console driver patches (mouse button state, A_DIM,
    wide-char declarations): scripts/patches/
  * scripts/bootstrap_msys2.sh builds the same release natively in MSYS2
    UCRT64; PR #1's MINGW64 notes now point there
  * vendor/tre-regex (musl's TRE) provides <regex.h> on MinGW

UTF-8
  * paths cross the system call boundary as UTF-16 (*W APIs); console code
    pages set to 65001 and restored on exit; files are read and written in
    binary mode
  * child output that is not valid UTF-8 is decoded from the console, OEM or
    ANSI system code page
  * read_file hides CR; edit_file, apply_patch and write_file keep CRLF line
    endings and a UTF-8 BOM

OS layer and processes
  * os_dir_* and cst_fnmatch replace the POSIX-only directory walks in
    subagent, plugins, skills, undo and fs_tools; realpath / path_under and
    symlink rejection work on Windows
  * every child goes through CreateProcessW with its own environment block
    inside a Job Object, so timeouts and Esc end the whole process tree

Sandbox (auto mode, "auto · lowil")
  * run_shell runs with a restricted Low integrity token; the workspace gets
    an inheritable Low label once, the sandbox TEMP is labeled Low, and the
    credentials file gets a no-read-up label
  * drive roots, the profile and system folders are never labeled
  * network commands still ask, since Low IL does not block the network;
    Access denied and MSYS2's 0xc0000142 offer a rerun outside the sandbox
  * /sandbox lists labeled folders, /sandbox reset-labels restores them

TUI
  * raster console fonts are switched to Consolas / NSimSun while running
  * the home logo falls back to text when the console font lacks U+2580
  * mouse drag copy goes to the Windows clipboard

Distribution
  * scripts/install_windows.ps1 installs a Gitea release into
    %LOCALAPPDATA%\Programs\cst-agent and adds it to the user PATH;
    cst-agent-update.cmd reruns it; scripts/release_windows.sh uploads the
    zip with the token taken from the environment
  * scripts/run_windows.bat is gone; docs/README-windows.md is rewritten

Tests
  * new test_lowil, test_win_utf8 and test_os_dir; tests made portable
    (cst_test_util.h)
  * scripts/win_test.sh and scripts/winvm/ run the suite on English and
    Chinese Windows Server VMs as Administrator, a standard user and a
    Chinese user name: 29/29 on all six
2026-10-06 23:08:14 +08:00
XYZ 3db33eddac Windows: make the CMake build work with MSYS2's native toolchain 2026-10-06 16:13:45 +08:00
WHC 1c26cc6e30 TUI: mouse drag selection with OSC 52 copy; Markdown emphasis follows CommonMark; v0.5.0
- Drag, double-click (word) and triple-click (line) selection in the log,
  auto-scroll at the edges, soft-wrapped lines joined on copy.
- sashidown ANSI renderer: delimiter runs with flanking rules, so
  intraword underscores (test_apply_patch.c) stay literal; unmatched
  * _ and backticks are shown as-is; * and _ do not close each other.
- tests: test_textsel, test_markdown.
2026-10-06 14:24:42 +08:00
WHC 7d3ec9fcb9 Extensions: skills, plugins, MCP, sub-agents; configurable keys
- Skills (SKILL.md discovery, skill tool, /skills /skill)
- plugin.json exec tools with permission prompts, timeouts and workspace trust (/plugins)
- MCP stdio client: JSON-RPC initialize/tools/list/tools/call, mcp__server__tool, /mcp and sidebar status
- task tool with general/explore/plan and .agent/agents/*.md roles, parallel read-only runs, cancel propagation, /agents
- Keymap with Ctrl+X leader, keybinds.json overrides and /keys panel
- Collapsed thinking, throttled streaming Markdown, leaner tool output, parallel read-only tools
- Spawn: close-on-exec pipes and a process-wide fork lock
- Tests for keymap, skills, plugins, MCP, sub-agents, shell compaction; docs/plugins.md
2026-10-05 14:55:31 +08:00
WHC ef63f6d612 OpenCode-style TUI, model probing, sandboxed auto approval
- TUI: centered home screen with logo, boxed input with mode line, sidebar
  (>=120 cols), Ctrl+P palette, Tab Build/Plan, Shift+Tab approval cycle,
  mouse (cards, cursor, pickers, wheel), /sidebar /mouse /approval
- /models probing: key check on entry (401 re-asks), API models in /model
- Shell sandbox in C: Linux Landlock (writes limited to workspace/tmp,
  ABI>=4 blocks TCP), macOS sandbox_init, rules fallback elsewhere
- Approval modes ask/auto/yolo (default auto); read-only command whitelist;
  ask to rerun outside the sandbox when a command looks blocked
- Upgradable bootstrap scripts (git pull --ff-only, rebuild, reinstall) and
  cst-agent-update; cst-agent --version
- tests: test_sandbox, test_models
2026-10-05 12:34:46 +08:00
WHC 2fde898da0 Usability pass: tool registry, TUI polish, saved keys and settings
Tools
- Table-driven tool registry with permission classes and default/minimal
  profiles; new tools: edit_file, list_dir, glob, grep, delete_file,
  move_file, todo_write, web_fetch, ask_user (plus read_file paging).
- Built-in Myers diff; write tools return unified diffs.
- Persistent permission rules (.agent/permissions.json), per-turn undo
  snapshots (.agent/undo), AGENTS.md project notes, auto-compact at 80%
  of the model context, cancellable run_shell with process-group kill.

TUI
- Table-driven slash commands: /provider /key /effort /status /tools
  /permissions /yolo /undo /retry /diff /export /copy /rename /delete
  /init /max-steps /todo, with / and @ completion.
- Permission modal with diff and prefix rules, ask_user modal, todo
  panel, header with model/effort/context, bracketed paste, line editing,
  wide-char cursor, NO_COLOR and ASCII fallback; Esc never quits.

Startup and configuration
- API keys are entered in the TUI (hidden) and saved per provider in
  <config>/credentials (0600); env variables are only a fallback.
- Last provider, per-provider model and reasoning effort are remembered
  in <config>/settings.json; --effort/-e and /effort send
  reasoning_effort (low|medium|high|max) to models that accept it.
- DeepSeek preset uses deepseek-flash / deepseek-v4-pro.
- Session flags --new/--continue/--resume/--list-sessions, --yolo,
  --confirm.

Compatibility and tests
- ncurses detection, macOS/Homebrew support, make install, XDG config
  dir, POSIX cleanups; Gitea CI (gcc/clang/asan/musl/macOS).
- Unit tests for diff, fs tools, registry, undo/perms and config;
  e2e fixtures multi_file_refactor and ask_or_todo; vendored cJSON.
2026-10-05 01:47:01 +08:00
WHCandCursor 1f1fcba7ad Initial CST-Agent: portable Linux/Termux/Windows coding agent.
Vendored sashidown, OpenAI-compatible env (OPENAI_*), and bootstrap scripts.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-07 22:42:32 +08:00