v0.8.6: general mode, clipboard text, PDF text extraction

Working mode: --mode coding|general (CST_MODE, settings.json, /mode, WebUI run settings). general swaps the default framing for a general assistant one -- workflow, safety notes, tool wording (run_shell, the subagents) -- and /status shows it; minimal (the paper profile) stays byte-frozen. The prompt state carries the mode so a switch leaves a system note in history. Clipboard: clipboard_read / clipboard_write tools (16 MiB cap read, default 64 KiB window; writing is a WRITE permission with a preview) on pbcopy / wl-copy / xclip / pbpaste / wl-paste / xclip and the Win32 clipboard. In the TUI, /attach paste falls back to clipboard text when there is no image on it. PDF: a dependency-free text extractor (src/pdf_text.c): inflate, Flate/ASCIIHex/ASCII85, PNG/TIFF predictors, layout-independent object scan, object streams, page tree walk with inherited resources, content lexer (Tj/TJ/'/" and the Td/TD/T*/Tm spacing heuristics), per-font ToUnicode CMaps and inline images skipped. Encrypted files and pages with no text layer are refused with the reason. Attachments: /attach (a path or files dropped on the terminal) now take images, PDFs and text. A PDF is stored as its text layer with the mime still saying application/pdf and its page count; anything else has to be UTF-8 text. Documents travel inline as text parts, so CST_NO_IMAGES and text-only models no longer drop them, while images keep their old path. Tests: test_pdf_text (plain, bare and zlib-framed Flate, inline image, CID + ToUnicode, object stream, error paths), documents in test_attach, inlined documents in test_llm_body, mode in test_config.
2026-10-11 11:09:39 +08:00
parent 50abcf1a91
commit e0b0eddf3a
28 changed files with 3291 additions and 111 deletions
@@ -390,6 +390,175 @@ int cst_clipboard_image(char **data, size_t *n, char *err, size_t err_sz) {

 #endif

+/* --- text clipboard ------------------------------------------------------ */
+
+#ifdef _WIN32
+
+int cst_clipboard_text(char **data, size_t *n, char *err, size_t err_sz) {
+  *data = NULL;
+  *n = 0;
+  if (!IsClipboardFormatAvailable(CF_UNICODETEXT) || !OpenClipboard(NULL)) {
+    set_err(err, err_sz, "no text on the clipboard");
+    return -1;
+  }
+  HANDLE h = GetClipboardData(CF_UNICODETEXT);
+  const wchar_t *w = h ? GlobalLock(h) : NULL;
+  if (!w) {
+    if (h)
+      GlobalUnlock(h);
+    CloseClipboard();
+    set_err(err, err_sz, "no text on the clipboard");
+    return -1;
+  }
+  char *utf8 = os_wide_to_utf8(w);
+  size_t len = utf8 ? strlen(utf8) : 0;
+  GlobalUnlock(h);
+  CloseClipboard();
+  if (!utf8 || !len) {
+    free(utf8);
+    set_err(err, err_sz, "no text on the clipboard");
+    return -1;
+  }
+  if (len > CST_CLIPBOARD_TEXT_MAX) {
+    free(utf8);
+    set_err(err, err_sz, "clipboard text is too large");
+    return -1;
+  }
+  *data = utf8;
+  *n = len;
+  return 0;
+}
+
+int cst_clipboard_set_text(const char *text, size_t n, char *err,
+                           size_t err_sz) {
+  if (!text || os_clipboard_set(text, n) != 0) {
+    set_err(err, err_sz, "could not put text on the clipboard");
+    return -1;
+  }
+  return 0;
+}
+
+#else
+
+/* stdout of a clipboard reader, capped and NUL-terminated. */
+static int clip_read(const char *cmd, const char *tool, char **data, size_t *n,
+                     char *err, size_t err_sz) {
+  os_run_result_t r;
+  memset(&r, 0, sizeof(r));
+  if (os_run_shell_c(NULL, cmd, CST_CLIPBOARD_TEXT_MAX + 1, &r) != 0) {
+    os_run_result_free(&r);
+    set_err(err, err_sz, "could not read the clipboard");
+    return -1;
+  }
+  if (r.exit_code != 0 || r.out_len == 0) {
+    int missing = r.exit_code == 127;
+    os_run_result_free(&r);
+    if (missing) {
+      char msg[96];
+      snprintf(msg, sizeof(msg), "reading the clipboard needs %s", tool);
+      set_err(err, err_sz, msg);
+    } else {
+      set_err(err, err_sz, "no text on the clipboard");
+    }
+    return -1;
+  }
+  if (r.out_len > CST_CLIPBOARD_TEXT_MAX) {
+    os_run_result_free(&r);
+    set_err(err, err_sz, "clipboard text is too large");
+    return -1;
+  }
+  char *copy = malloc(r.out_len + 1);
+  if (!copy) {
+    os_run_result_free(&r);
+    set_err(err, err_sz, "out of memory");
+    return -1;
+  }
+  memcpy(copy, r.out, r.out_len);
+  copy[r.out_len] = 0;
+  os_run_result_free(&r);
+  *data = copy;
+  *n = r.out_len;
+  return 0;
+}
+
+int cst_clipboard_text(char **data, size_t *n, char *err, size_t err_sz) {
+  *data = NULL;
+  *n = 0;
+#ifdef __APPLE__
+  return clip_read("pbpaste 2>/dev/null", "pbpaste", data, n, err, err_sz);
+#else
+  const char *wl = getenv("WAYLAND_DISPLAY");
+  if (wl && *wl)
+    return clip_read("wl-paste --type text/plain --no-newline 2>/dev/null",
+                     "wl-clipboard (wl-paste)", data, n, err, err_sz);
+  const char *x = getenv("DISPLAY");
+  if (x && *x)
+    return clip_read("xclip -selection clipboard -o 2>/dev/null", "xclip",
+                     data, n, err, err_sz);
+  set_err(err, err_sz, "no clipboard here (no Wayland or X11 display)");
+  return -1;
+#endif
+}
+
+int cst_clipboard_set_text(const char *text, size_t n, char *err,
+                           size_t err_sz) {
+  if (!text)
+    return -1;
+  if (n > CST_CLIPBOARD_TEXT_MAX) {
+    set_err(err, err_sz, "text is too large for the clipboard");
+    return -1;
+  }
+  const char *fmt = NULL, *tool = NULL;
+#ifdef __APPLE__
+  fmt = "pbcopy < '%s'";
+  tool = "pbcopy";
+#else
+  if (getenv("WAYLAND_DISPLAY")) {
+    fmt = "wl-copy < '%s'";
+    tool = "wl-clipboard (wl-copy)";
+  } else if (getenv("DISPLAY")) {
+    fmt = "xclip -selection clipboard -i < '%s'";
+    tool = "xclip";
+  }
+#endif
+  if (!fmt) {
+    set_err(err, err_sz, "no clipboard here (no Wayland or X11 display)");
+    return -1;
+  }
+  char tmp[OS_PATH_MAX];
+  int fd = os_mkstemp(tmp, sizeof(tmp), "cst-clip");
+  if (fd < 0) {
+    set_err(err, err_sz, "could not create a temporary file");
+    return -1;
+  }
+  FILE *fp = fdopen(fd, "wb");
+  int ok = fp && fwrite(text, 1, n, fp) == n && fclose(fp) == 0;
+  if (!ok) {
+    if (fp)
+      fclose(fp);
+    remove(tmp);
+    set_err(err, err_sz, "could not write the text");
+    return -1;
+  }
+  char cmd[OS_PATH_MAX + 64];
+  snprintf(cmd, sizeof(cmd), fmt, tmp);
+  os_run_result_t r;
+  memset(&r, 0, sizeof(r));
+  int rc = os_run_shell_c(NULL, cmd, 4096, &r);
+  int code = r.exit_code;
+  os_run_result_free(&r);
+  remove(tmp);
+  if (rc != 0 || code != 0) {
+    char msg[96];
+    snprintf(msg, sizeof(msg), "writing the clipboard needs %s", tool);
+    set_err(err, err_sz, msg);
+    return -1;
+  }
+  return 0;
+}
+
+#endif
+
 static int hexval(int c) {
  if (c >= '0' && c <= '9')
    return c - '0';