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.

CMakeLists.txt

@@ -95,6 +95,7 @@ set(CST_CORE_SOURCES
   src/subagent.c
   src/attach.c
   src/clipboard.c
+  src/pdf_text.c
   src/session.c
   src/tools/tools.c
   src/tools/patch.c
@@ -279,7 +280,7 @@ endif()
 enable_testing()
 set(_CST_SMALL_TESTS test_ctl_frontier test_ctl_heredoc test_json_baseline
     test_replay_starvation test_replay_real test_mm_tool test_textsel
-    test_markdown)
+    test_pdf_text test_markdown)
 foreach(t ${_CST_SMALL_TESTS})
   if(t STREQUAL test_textsel)
     add_executable(${t} tests/${t}.c src/textsel.c src/os_compat.c src/os_win.c
@@ -287,6 +288,12 @@ foreach(t ${_CST_SMALL_TESTS})
     if(WIN32)
       target_link_libraries(${t} PRIVATE advapi32 user32)
     endif()
+  elseif(t STREQUAL test_pdf_text)
+    add_executable(${t} tests/${t}.c src/pdf_text.c src/os_compat.c src/os_win.c
+      src/util.c)
+    if(WIN32)
+      target_link_libraries(${t} PRIVATE advapi32 user32)
+    endif()
   elseif(t STREQUAL test_markdown)
     add_executable(${t} tests/${t}.c)
     target_include_directories(${t} PRIVATE "${SD_DIR}/include")

Makefile

@@ -96,6 +96,7 @@ CORE_SRC = \
 	src/keymap.c \
 	src/skills.c \
 	src/extensions.c src/plugins.c src/mcp.c src/subagent.c src/attach.c src/clipboard.c \
+	src/pdf_text.c \
 	src/session.c \
 	src/tools/tools.c \
 	src/tools/patch.c \
@@ -135,6 +136,7 @@ TESTS = \
 	tests/test_apply_patch \
 	tests/test_session_roundtrip \
 	tests/test_attach \
+	tests/test_pdf_text \
 	tests/test_shell \
 	tests/test_diff \
 	tests/test_tools_fs \
@@ -229,6 +231,9 @@ tests/test_mm_tool: tests/test_mm_tool.c src/mm_tool.c include/mm_tool.h $(TEST_
 tests/test_textsel: tests/test_textsel.c src/textsel.c $(TEST_OS_SRC) include/cst_textsel.h
 	$(CC) $(CFLAGS) $(CPPFLAGS) -o $@ tests/test_textsel.c src/textsel.c $(TEST_OS_SRC) $(TEST_SYS_LIBS)
 
+tests/test_pdf_text: tests/test_pdf_text.c src/pdf_text.c include/cst_pdf.h $(TEST_OS_SRC)
+	$(CC) $(CFLAGS) $(CPPFLAGS) -o $@ tests/test_pdf_text.c src/pdf_text.c $(TEST_OS_SRC) $(TEST_SYS_LIBS)
+
 tests/test_markdown: tests/test_markdown.c $(SD_DIR)/libsashidown.a
 	$(CC) $(CFLAGS) $(CPPFLAGS) -o $@ tests/test_markdown.c $(LDFLAGS) -lsashidown -lm
 

README.md

@@ -233,6 +233,7 @@ Windows x86_64 的 zip 和安装包（Debian 的 mingw-w64 UCRT gcc + NSIS）。
 |---|---|
 | `CST_PROTOCOL` / `--protocol` | 工具调用协议（`native-eos`） |
 | `CST_TOOLS` / `--tools` | 工具集：`default`（全部）/ `minimal`（论文 4 件套） |
+| `CST_MODE` / `--mode` | 工作模式：`coding`（默认，代码口径）/ `general`（通用助手口径） |
 | `CST_EFFORT` / `--effort` | 推理强度 `low` / `medium` / `high` / `max` |
 | `CST_CONFIRM` / `--confirm` | 哪些类别要确认：`shell,write,net`（默认）或 `none` |
 | `CST_MAX_STEPS` / `--max-steps` | 每个用户回合最多调用模型几次（30） |
@@ -276,6 +277,7 @@ cst-agent --headless --prompt 'List files'
 | `-y` / `--yolo` | 等同 `--approval yolo`，只对本次运行有效 |
 | `-C LIST` / `--confirm LIST` | 需要确认的类别：`shell,write,net` 的任意组合或 `none` |
 | `-T PROFILE` / `--tools PROFILE` | `default` 或 `minimal` |
+| `-M MODE` / `--mode MODE` | 工作模式 `coding`（默认）/ `general`，也读 `CST_MODE`，并记进 `settings.json` |
 | `-P NAME` / `-m NAME` / `-e LEVEL` | 本次使用的 provider / 模型 / 推理强度（不传则用上次的） |
 | `-a` / `--ask-key` | 在命令行输入并保存当前 provider 的 key |
 
@@ -297,6 +299,8 @@ cst-agent --headless --prompt 'List files'
 | `delete_file` / `move_file` | 写 | 删除 / 移动（重命名）文件 |
 | `run_shell` | shell | 非交互命令，超时整组进程被杀，Esc 可中断 |
 | `web_fetch` | 网络 | 抓取 URL，HTML 转纯文本 |
+| `clipboard_read` | 读 | 读系统剪贴板里的文本（`max_bytes` 默认 64 KiB，超出截断并说明） |
+| `clipboard_write` | 写 | 把文本放进系统剪贴板（按写类权限确认；本机走 pbcopy / wl-copy / xclip / Win32 API） |
 | `todo_write` | 元 | 维护任务清单（TUI 右侧面板，Ctrl+T 开关） |
 | `ask_user` | 询问 | 向用户提问（可给选项）；headless 下返回错误让模型自行决定 |
 | `skill` | 元 | 加载一个 skill 的说明（`SKILL.md`）或其中的文件；有 skill 时才出现 |
@@ -308,6 +312,26 @@ cst-agent --headless --prompt 'List files'
 `--tools minimal` 只保留 `read_file` / `run_shell` / `write_file` / `apply_patch`（论文实验口径）。
 TUI 中 `/tools off NAME`、`/tools on NAME` 可临时开关单个工具。
 
+### 工作模式（coding / general）
+
+`--mode general`（或 TUI 里 `/mode general`、WebUI 运行设置里的「工作模式」、`CST_MODE=general`）把默认口径
+从"代码助手"换成"通用助手"：工作流从改代码/跑测试换成"先弄清要什么、再动手、给出处和不确定的地方"，
+工具说明从"仓库"改成"文件与数据"，并说明 `web_fetch` 可以拿外部资料；`/status` 第一行显示当前模式，
+切换后 history 里会留一条系统提示。默认仍是 `coding`，选择记在 `settings.json`；
+`--tools minimal`（论文口径）的提示词按字节冻结，不受模式影响。
+
+### 剪贴板与文档附件
+
+- **剪贴板**：`clipboard_read` / `clipboard_write` 两个工具（写剪贴板是不可逆发射，要确认）；
+  TUI 里 `/attach paste` 在剪贴板里没有图片时，把剪贴板的**文本**放进输入框（丢掉 CR 与控制字节，尊重输入长度上限）。
+- **附件**（`/attach <path>`、拖入终端、剪贴板图片都算）：图片按原样存进会话目录，发给模型时是 image part；
+  **PDF 在摄取时就抽出文本层**（零依赖解析器：Flate / ASCIIHex / ASCII85、对象流、CID 字体 ToUnicode、
+  内联图像跳过），存的是文本、`mime` 仍是 `application/pdf`；其余文件必须是 UTF-8 文本。
+  文档以 **text part 内联**发出，所以不受 `CST_NO_IMAGES` 或非视觉模型影响；图片照旧会被换成一行"未发送"说明。
+  上限：单个附件 ≤16 MB（文档文本 ≤4 MiB），每条消息最多 8 个。
+  加密 PDF、扫描件（无文本层）会被明确拒绝并说明原因；
+  `view_image` 仍只收图片，文本/PDF 走 `/attach`。
+
 ### 权限、撤销与项目说明
 
 - **审批模式**（Shift+Tab 循环切换，`/approval`，`--approval`，`CST_APPROVAL`）：
@@ -426,6 +450,7 @@ Thought（推理过程）默认折叠成一行“Thought · 3.2s”，生成中
 | `/provider [name]`、`/model [name]`、`/effort [level]` | 切换 provider（缺 key 时当场输入并用 `/models` 校验）、模型（列表优先显示 API 实际返回的模型，标 `(api)`）、推理强度；都会记住 |
 | `/key` | 输入或更换当前 provider 的 API key（遮罩输入并保存） |
 | `/protocol [name]` | 切换工具调用协议 |
+| `/mode [coding\|general]` | 工作模式（通用助手 / 代码助手口径） |
 | `/tools [on\|off NAME\|minimal\|default]` | 查看或开关工具 |
 | `/approval [ask\|auto\|yolo]` *、`/yolo` * | 审批模式；本次开关 yolo |
 | `/permissions [reset]` *、`/max-steps [N]` * | 权限规则、每轮步数 |
@@ -435,6 +460,7 @@ Thought（推理过程）默认折叠成一行“Thought · 3.2s”，生成中
 | `/diff [path]` * | `git status` + `git diff` |
 | `/compact` | 手动压缩上下文 |
 | `/export [file]` *、`/copy` * | 导出 Markdown 记录；复制上一条回复（OSC 52，需终端支持） |
+| `/attach [path\|paste\|list\|clear]` | 给下一条消息带附件：图片、PDF（自动取文本层）、文本文件；`paste` 优先取剪贴板图片，没有就把剪贴板文本放进输入框 |
 | `/web` * | 后台起一个 WebUI 进程（同 workspace、新会话，日志写到 `.agent/webui.log`） |
 | `/init` | 让 agent 写 `AGENTS.md` |
 | `/details` *、`/thinking [on\|off]`、`/keys` * | 展开全部 tool 输出；Thought 默认展开/折叠；快捷键列表 |

include/cst_agent.h

@@ -47,15 +47,18 @@ int cst_protocol_is_text(cst_protocol_t p);
 /* Eager protocols execute a call during the stream, at confirmation time. */
 int cst_protocol_is_eager(cst_protocol_t p);
 
-/* One image carried by a message (see cst_attach.h). The bytes live beside
+/* One file carried by a message (see cst_attach.h): an image, or a document
- * the session; this is the metadata plus the name of the stored copy. */
+ * whose stored payload is its text. The payload lives beside the session;
+ * this is the metadata plus the name of the stored copy. */
 typedef struct {
   char id[32];      /* unique inside the session ("img-1a2b3c4d") */
   char name[256];   /* display name (original file name) */
-  char mime[32];    /* image/png, image/jpeg, image/gif, image/webp, image/bmp */
+  char mime[32];    /* image/png, ...; application/pdf for a PDF whose text
+                     * layer the stored file holds; text/plain for text */
   char rel[256];    /* file name inside the session's attachment directory */
-  long long bytes;  /* stored size */
+  long long bytes;  /* stored size (the text, for documents) */
   int width, height; /* pixels, 0 when the header could not be read */
+  int pages;        /* PDF page count, 0 for anything else */
   char detail[8];   /* auto | low | high (wire hint, "" = auto) */
   char origin[32];  /* user | view_image | mcp (for display only) */
 } cst_attachment_t;
@@ -82,6 +85,7 @@ typedef struct {
   char model[128];
   char provider[32];
   char effort[16];      /* low | medium | high | max */
+  char mode[16];        /* coding | general (CST_DEFAULT_MODE) */
   cst_protocol_t protocol;
   int max_steps;        /* model calls per user turn */
   size_t tool_out_cap;  /* bytes of one tool output sent to the model */
@@ -114,6 +118,14 @@ typedef enum {
 const char *cst_approval_name(int a);
 int cst_approval_parse(const char *s, int *out);
 
+/* Working mode: how the system prompt frames the agent. "coding" (default)
+ * is code framed; "general" is for tasks that are not about a codebase
+ * (documents, data, research, everyday files). Orthogonal to plan mode. */
+#define CST_DEFAULT_MODE "coding"
+int cst_mode_valid(const char *m);
+/* Canonical name of m, or the default when m is unknown / empty. */
+const char *cst_mode_name(const char *m);
+
 typedef struct cst_session cst_session_t;
 typedef struct cst_agent cst_agent_t;
 
@@ -406,13 +418,14 @@ int cst_creds_resolve(const char *provider, char *out, size_t out_sz,
 /* Hidden console prompt (no echo). */
 int cst_creds_prompt_console(const char *provider, char *out, size_t out_sz);
 
-/* Last used provider, model per provider and effort, in
+/* Last used provider, model per provider, effort and working mode, in
  * <config>/settings.json. */
 #define CST_SETTINGS_MAX_MODELS 16
 #define CST_SETTINGS_MAX_TRUSTED 32
 typedef struct {
   char provider[32];
   char effort[16];
+  char mode[16];     /* coding | general, "" = not chosen yet */
   char approval[8]; /* "" = not chosen yet */
   int show_thinking; /* TUI: Thought blocks start expanded */
   /* workspaces whose .agent/plugins and .agent/mcp.json may run */
@@ -427,11 +440,13 @@ typedef struct {
 int cst_settings_load(cst_settings_t *s);
 int cst_settings_save(const cst_settings_t *s);
 const char *cst_settings_model(const cst_settings_t *s, const char *provider);
-/* Record cfg's provider, model and effort as the last used ones. */
+/* Record cfg's provider, model, effort and mode as the last used ones. */
 int cst_settings_remember(const cst_agent_config_t *cfg);
 /* Record an approval mode the user picked (CST_APPROVAL_*). */
 int cst_settings_remember_approval(int approval);
 int cst_settings_remember_thinking(int show_thinking);
+/* Record the working mode the user picked (coding | general). */
+int cst_settings_remember_mode(const char *mode);
 /* Workspace trust for project plugins / MCP servers (by real path). */
 int cst_settings_trusted(const char *workspace);
 int cst_settings_trust(const char *workspace, int on);

include/cst_attach.h

@@ -9,16 +9,24 @@
 extern "C" {
 #endif
 
-/* --- image attachments ---------------------------------------------------
+/* --- attachments ---------------------------------------------------------
- * An attachment is a validated copy of an image file, stored beside the
+ * An attachment is a validated copy of a file, stored beside the session so
- * session so the bytes a model is shown stay the bytes that were picked.
+ * what a model is shown stays what was picked. Images are stored as they are
- * Only the metadata travels in the JSONL; the bytes are encoded into the
+ * and encoded into the request when it is built; a PDF is reduced to its text
- * request when it is built. */
+ * layer and a text file is stored as is, both of which travel inline as text
+ * (so a text-only model still gets them). Only the metadata goes in the
+ * JSONL. */
 
-/* Supported: PNG, JPEG, GIF, WebP, BMP (static images). */
+/* Supported: PNG, JPEG, GIF, WebP, BMP (static images), PDF, UTF-8 text. */
-#define CST_ATTACH_MAX_BYTES (16 * 1024 * 1024) /* one stored image */
+#define CST_ATTACH_MAX_BYTES (16 * 1024 * 1024) /* one picked file */
 #define CST_ATTACH_MAX_TOTAL (32 * 1024 * 1024) /* per request */
 #define CST_ATTACH_MAX_COUNT 8                  /* per message */
+/* Text stored and inlined per document (a PDF also caps its text here). */
+#define CST_ATTACH_TEXT_MAX (4 * 1024 * 1024)
+
+/* Images go on the wire as image parts; everything else is inlined as text. */
+int cst_attach_is_image(const cst_attachment_t *a);
+int cst_attach_is_text(const cst_attachment_t *a);
 
 /* Magic-byte test: 0 and a canonical mime when data holds a supported
  * image, -1 otherwise (an extension alone never decides). */
@@ -35,23 +43,25 @@ int cst_attach_dir(const char *session_path, char *out, size_t out_sz);
 int cst_attach_full_path(const char *session_path, const cst_attachment_t *a,
                          char *out, size_t out_sz);
 
-/* Read src_path, verify it is a supported image within limits, and copy it
+/* Read src_path and copy it into the session's attachment directory: an image
- * into the session's attachment directory. Returns a malloc'd entry the
+ * as it is, a PDF as its extracted text, anything else only when it is text.
- * caller owns (cst_attach_free), or NULL with err filled. */
+ * Returns a malloc'd entry the caller owns (cst_attach_free), or NULL with
+ * err filled. */
 cst_attachment_t *cst_attach_import_file(const char *session_path,
                                          const char *src_path, char *err,
                                          size_t err_sz);
-/* Store already-read bytes (clipboard, downloads); name is display-only. */
+/* Store already-read image bytes (clipboard, downloads); name is
+ * display-only. */
 cst_attachment_t *cst_attach_import_bytes(const char *session_path,
                                           const char *name, const char *data,
                                           size_t n, char *err, size_t err_sz);
 
-/* Validate and read back a stored image, or NULL when it is gone. */
+/* Validate and read back a stored payload, or NULL when it is gone. */
 char *cst_attach_read(const char *session_path, const cst_attachment_t *a,
                       size_t *out_len, char *err, size_t err_sz);
-/* "data:image/png;base64,...." for the wire; NULL when the file is gone. */
+/* "data:image/png;base64,...." for the wire; images only, NULL otherwise. */
 char *cst_attach_data_url(const char *session_path, const cst_attachment_t *a);
-/* "1920x1080 PNG 412 KB" style one-liner for prompts and the UI. */
+/* "1920x1080 png 412 KB" / "pdf 1.2 MB, 12 pages" one-liner for prompts. */
 void cst_attach_describe(const cst_attachment_t *a, char *out, size_t out_sz);
 
 void cst_attach_free(cst_attachment_t *a);

include/cst_clipboard.h

@@ -13,6 +13,20 @@ extern "C" {
  * ("no image on the clipboard", "install wl-clipboard", ...). */
 int cst_clipboard_image(char **data, size_t *n, char *err, size_t err_sz);
 
+/* Cap on text moved through the clipboard (read and write). */
+#define CST_CLIPBOARD_TEXT_MAX (1024 * 1024)
+
+/* UTF-8 text on the system clipboard: Wayland (wl-paste), X11 (xclip),
+ * macOS (pbpaste), Windows (CF_UNICODETEXT). Returns 0 with *data malloc'd
+ * and NUL-terminated, or -1 with err filled in ("no text on the clipboard",
+ * "reading the clipboard needs wl-clipboard", ...). */
+int cst_clipboard_text(char **data, size_t *n, char *err, size_t err_sz);
+
+/* Replace the clipboard with UTF-8 text: wl-copy / xclip / pbcopy, or the
+ * Windows clipboard API. Returns 0 on success, else -1 with err. */
+int cst_clipboard_set_text(const char *text, size_t n, char *err,
+                           size_t err_sz);
+
 /* Windows CF_DIB bytes (BITMAPINFOHEADER + pixels) as an image file: a PNG
  * for uncompressed 24/32-bit bitmaps, else a BMP. NULL when malformed. */
 char *cst_dib_to_image(const void *dib, size_t sz, size_t *n);

include/cst_pdf.h

@@ -0,0 +1,27 @@
+#ifndef CST_PDF_H
+#define CST_PDF_H
+
+#include <stddef.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Text layer of a PDF, in page order, with no external dependency (no
+ * poppler, no zlib): classic objects and object streams, FlateDecode plus
+ * ASCIIHex/ASCII85, PNG/TIFF predictors, Tj/TJ/'/" text with per-font
+ * ToUnicode CMaps and a WinAnsi / Latin-1 fallback. Scanned pages have no
+ * text layer and are reported as such.
+ * Returns a malloc'd NUL-terminated UTF-8 string, or NULL with err filled in
+ * ("PDF is encrypted ...", "no extractable text ..."). *pages (optional) gets
+ * the page count; the result is truncated at CST_PDF_TEXT_MAX bytes. */
+char *cst_pdf_text(const void *data, size_t n, int *pages, char *err,
+                   size_t err_sz);
+
+#define CST_PDF_TEXT_MAX (4u * 1024u * 1024u)
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

include/cst_version.h

@@ -3,7 +3,7 @@
 
 #define CST_VERSION_MAJOR 0
 #define CST_VERSION_MINOR 8
-#define CST_VERSION_PATCH 5
+#define CST_VERSION_PATCH 6
 
 #define CST_VERSION_STR_(x) #x
 #define CST_VERSION_STR(x) CST_VERSION_STR_(x)

src/agent_loop.c

@@ -177,8 +177,62 @@ static int tool_on(const cst_agent_config_t *cfg, const char *name) {
   return cst_tool_active(cfg, cst_tool_find(name));
 }
 
+/* /mode general (cst_mode_name covers "" and unknown values). */
+static int general_mode(const cst_agent_config_t *cfg) {
+  return cfg && strcmp(cst_mode_name(cfg->mode), "general") == 0;
+}
+
+/* Workflow for /mode general: gather, then do the work, then check it. */
+static void put_workflow_general(cst_buf_t *b, const cst_agent_config_t *cfg) {
+  cst_buf_puts(b, "\nWorkflow:\n1) Gather what you need");
+  const char *explore[] = {"list_dir", "glob", "grep"};
+  int n = 0;
+  for (int i = 0; i < 3; i++) {
+    if (tool_on(cfg, explore[i]))
+      cst_buf_printf(b, "%s%s", n++ ? ", " : " (", explore[i]);
+  }
+  if (n)
+    cst_buf_puts(b, ")");
+  if (tool_on(cfg, "read_file"))
+    cst_buf_puts(b, "; read big files in slices with read_file offset/limit, "
+                    "and use the documents the user attached");
+  cst_buf_puts(b, ".\n2) Do the work");
+  n = 0;
+  if (tool_on(cfg, "write_file")) {
+    cst_buf_puts(b, ": write_file for new files");
+    n++;
+  }
+  if (tool_on(cfg, "edit_file"))
+    cst_buf_printf(b, "%sedit_file for small exact replacements",
+                   n++ ? ", " : ": ");
+  if (tool_on(cfg, "apply_patch"))
+    cst_buf_printf(b, "%sapply_patch for multi-hunk diffs to existing files",
+                   n++ ? ", " : ": ");
+  if (tool_on(cfg, "run_shell"))
+    cst_buf_printf(b, "%srun_shell for commands, computations, data "
+                      "processing and other CLIs",
+                   n++ ? ", " : ": ");
+  cst_buf_puts(b, ".\n");
+  if (tool_on(cfg, "run_shell"))
+    cst_buf_puts(b, "3) Check the result before saying it works (re-read it, "
+                    "run it, or verify the numbers); fix and re-run until it "
+                    "holds.\n");
+  if (tool_on(cfg, "todo_write"))
+    cst_buf_puts(b, "- For work with several steps keep a todo list with "
+                    "todo_write and update it as you go.\n");
+  if (tool_on(cfg, "ask_user"))
+    cst_buf_puts(b, "- Use ask_user only when a decision is truly the user's; "
+                    "otherwise choose sensibly and say so.\n");
+  cst_buf_puts(b, "Finish with a short plain-text summary of the result.\n"
+                  "Never invent other tool names.\n");
+}
+
 /* Workflow section for the default tool profile; names only active tools. */
 static void put_workflow(cst_buf_t *b, const cst_agent_config_t *cfg) {
+  if (general_mode(cfg)) {
+    put_workflow_general(b, cfg);
+    return;
+  }
   cst_buf_puts(b, "\nWorkflow:\n1) Inspect only what you need");
   const char *explore[] = {"list_dir", "glob", "grep"};
   int n = 0;
@@ -235,6 +289,25 @@ static const char DEF_INTRO[] =
     "could not verify, say so.\n"
     "- Keep going until the task is done or truly blocked.\n\n";
 
+/* Same role, framed for /mode general: the workspace may hold documents,
+ * data or anything else, not just code. */
+static const char DEF_INTRO_GENERAL[] =
+    "You are CST-Agent, a general-purpose assistant working in the user's "
+    "local workspace. All tool paths are relative to the workspace root and "
+    "shell commands run there; the material you work on may be code, "
+    "documents, data or anything else.\n\n"
+    "Principles:\n"
+    "- Reply in the user's language. Be concise: lead with the result, no "
+    "filler.\n"
+    "- Understand before answering: read the files, documents and sources the "
+    "task refers to instead of guessing; never invent content, numbers or "
+    "tool results.\n"
+    "- Do what was asked, at the scope asked: leave unrelated files, data and "
+    "material alone.\n"
+    "- Check your work when you can (re-read it, run it, cross-check the "
+    "source); if you could not verify something, say so.\n"
+    "- Keep going until the task is done or truly blocked.\n\n";
+
 static void put_tool_use(cst_buf_t *b, const cst_agent_config_t *cfg) {
   cst_buf_puts(b, "\nTool use:\n");
   if (tool_on(cfg, "run_shell") &&
@@ -248,15 +321,26 @@ static void put_tool_use(cst_buf_t *b, const cst_agent_config_t *cfg) {
     cst_buf_puts(b, "- Read a file before editing it and again after a failed "
                     "edit. The `N|` prefixes in read_file output are not part "
                     "of the file.\n");
+  if (general_mode(cfg) && tool_on(cfg, "web_fetch"))
+    cst_buf_puts(b, "- Use web_fetch for pages the user points you to; say so "
+                    "when a page could not be fetched instead of guessing its "
+                    "content.\n");
   cst_buf_puts(b, "- When a call fails, read the error and change approach "
                   "instead of repeating the same call.\n");
 }
 
 static void put_safety(cst_buf_t *b, const cst_agent_config_t *cfg) {
-  cst_buf_puts(b, "\nSafety:\n"
+  if (general_mode(cfg))
-                  "- Do not commit, push or rewrite git history unless asked. "
+    cst_buf_puts(b, "\nSafety:\n"
-                  "Do not delete or overwrite files you did not create unless "
+                    "- Do not delete or overwrite files or data you did not "
-                  "the task requires it. Never print secrets or API keys.\n");
+                    "create unless the task requires it, and do not send the "
+                    "user's content anywhere the task did not ask for. Never "
+                    "print secrets or API keys.\n");
+  else
+    cst_buf_puts(b, "\nSafety:\n"
+                    "- Do not commit, push or rewrite git history unless asked. "
+                    "Do not delete or overwrite files you did not create unless "
+                    "the task requires it. Never print secrets or API keys.\n");
   if (tool_on(cfg, "run_shell"))
     cst_buf_puts(b, "- run_shell may run in a sandbox (writes only inside the "
                     "workspace and temp dir; the network works). If a command is "
@@ -365,7 +449,9 @@ char *cst_agent_build_prompt(const cst_agent_config_t *cfg, cst_protocol_t p,
                              const char *project_notes) {
   int minimal = !cfg || cfg->tool_profile == CST_TOOLS_MINIMAL;
   cst_buf_t b = {0};
-  cst_buf_puts(&b, minimal ? PROMPT_BASE : DEF_INTRO);
+  cst_buf_puts(&b, minimal ? PROMPT_BASE
+                           : general_mode(cfg) ? DEF_INTRO_GENERAL
+                                               : DEF_INTRO);
   if (cst_protocol_is_native(p))
     cst_buf_puts(&b, minimal ? SEC_NATIVE
                              : "Call tools through the native "
@@ -2241,11 +2327,12 @@ int cst_agent_undo_available(const cst_agent_t *a) {
  * later changes reach the model as persisted notes appended to the history,
  * which keeps the cached prefix intact. */
 
-#define PROMPT_VERSION 2
+#define PROMPT_VERSION 3
 
 typedef struct {
   int plan;
   char approval[96];
+  char mode[16];
   char branch[128];
   char day[16];
   char notes[24]; /* hash of AGENTS.md, "" = none */
@@ -2255,6 +2342,7 @@ static void state_now(const cst_agent_t *a, pstate_t *s) {
   memset(s, 0, sizeof(*s));
   s->plan = a->cfg.plan_mode;
   snprintf(s->approval, sizeof(s->approval), "%s", approval_desc(&a->cfg));
+  snprintf(s->mode, sizeof(s->mode), "%s", cst_mode_name(a->cfg.mode));
   git_branch(a->cfg.workspace_root, s->branch, sizeof(s->branch));
   today(s->day, sizeof(s->day));
   if (a->notes && a->notes[0])
@@ -2267,6 +2355,7 @@ static cJSON *state_json(const pstate_t *s) {
   cJSON *o = cJSON_CreateObject();
   cJSON_AddNumberToObject(o, "plan", s->plan);
   cJSON_AddStringToObject(o, "approval", s->approval);
+  cJSON_AddStringToObject(o, "mode", s->mode);
   cJSON_AddStringToObject(o, "branch", s->branch);
   cJSON_AddStringToObject(o, "day", s->day);
   cJSON_AddStringToObject(o, "notes", s->notes);
@@ -2282,6 +2371,7 @@ static void state_parse(const cJSON *o, pstate_t *s) {
   if (cJSON_IsString(v))                                                       \
     snprintf(s->field, sizeof(s->field), "%s", v->valuestring);
   STATE_STR("approval", approval)
+  STATE_STR("mode", mode)
   STATE_STR("branch", branch)
   STATE_STR("day", day)
   STATE_STR("notes", notes)
@@ -2293,6 +2383,7 @@ static char *system_meta(const cst_agent_t *a, const pstate_t *s) {
   cJSON_AddStringToObject(o, "protocol", cst_protocol_name(a->cfg.protocol));
   cJSON_AddNumberToObject(o, "pv", PROMPT_VERSION);
   cJSON_AddNumberToObject(o, "tools", a->cfg.tool_profile);
+  cJSON_AddStringToObject(o, "mode", cst_mode_name(a->cfg.mode));
   cJSON_AddItemToObject(o, "state", state_json(s));
   char *out = cJSON_PrintUnformatted(o);
   cJSON_Delete(o);
@@ -2312,10 +2403,13 @@ static int system_current(const cst_message_t *m, const cst_agent_config_t *c) {
   const cJSON *pv = cJSON_GetObjectItemCaseSensitive(meta, "pv");
   const cJSON *pr = cJSON_GetObjectItemCaseSensitive(meta, "protocol");
   const cJSON *tp = cJSON_GetObjectItemCaseSensitive(meta, "tools");
+  const cJSON *md = cJSON_GetObjectItemCaseSensitive(meta, "mode");
   int ok = cJSON_IsNumber(pv) && pv->valueint == PROMPT_VERSION &&
            cJSON_IsString(pr) &&
            strcmp(pr->valuestring, cst_protocol_name(c->protocol)) == 0 &&
            cJSON_IsNumber(tp) && tp->valueint == c->tool_profile;
+  ok = ok && cJSON_IsString(md) &&
+       strcmp(md->valuestring, cst_mode_name(c->mode)) == 0;
   cJSON_Delete(meta);
   return ok;
 }
@@ -2393,6 +2487,14 @@ static void sync_notes(cst_agent_t *a) {
                        "is available again.\n");
   if (strcmp(now.approval, was.approval) != 0)
     cst_buf_printf(&b, "[cst] Approval mode is now %s.\n", now.approval);
+  if (strcmp(now.mode, was.mode) != 0)
+    cst_buf_printf(&b,
+                   "[cst] Working mode is now %s%s. Earlier instructions about "
+                   "how to frame the work no longer apply.\n",
+                   now.mode,
+                   strcmp(now.mode, "general") == 0
+                       ? " (general: documents, data, research)"
+                       : " (coding: repo, build, tests)");
   if (strcmp(now.branch, was.branch) != 0)
     cst_buf_printf(&b, "[cst] The git branch is now %s.\n",
                    now.branch[0] ? now.branch : "(none)");

src/attach.c

@@ -4,6 +4,7 @@
 
 #include "cJSON.h"
 #include "cst_attach.h"
+#include "cst_pdf.h"
 #include "cst_util.h"
 #include "os_compat.h"
 
@@ -102,6 +103,9 @@ static int le16(const unsigned char *p) {
 }
 
 static const char *mime_of_ext(const char *mime) {
+  if (strcmp(mime, "application/pdf") == 0 ||
+      strcmp(mime, "text/plain") == 0)
+    return "txt"; /* a document is stored as the text it was reduced to */
   if (strcmp(mime, "image/png") == 0)
     return "png";
   if (strcmp(mime, "image/jpeg") == 0)
@@ -352,23 +356,73 @@ static void make_id(const char *name, const char *data, size_t n, char *out,
   snprintf(out, out_sz, "img-%08x", (unsigned)(h & 0xFFFFFFFFu));
 }
 
+/* n bytes, NUL-terminated: a text payload is handed around as a C string. */
+static char *memdup_z(const char *data, size_t n) {
+  char *copy = malloc(n + 1);
+  if (!copy)
+    return NULL;
+  memcpy(copy, data, n);
+  copy[n] = 0;
+  return copy;
+}
+
+/* What a picked file is, plus the payload to store for it: an image stays as
+ * it is, a PDF is reduced to its text layer (the mime still says PDF, the
+ * stored file holds text), anything else must be UTF-8 text. The caller frees
+ * the result; *out_len is its length. */
+static char *prepare(const char *data, size_t n, char *mime, size_t mime_sz,
+                     int *pages, size_t *out_len, char *err, size_t err_sz) {
+  *pages = 0;
+  *out_len = n;
+  if (cst_attach_sniff(data, n, mime, mime_sz) == 0) {
+    if (n > CST_ATTACH_MAX_BYTES) {
+      snprintf(err, err_sz, "image is %.1f MB; the limit is %d MB",
+               (double)n / (1024 * 1024), (int)(CST_ATTACH_MAX_BYTES >> 20));
+      return NULL;
+    }
+    char *copy = memdup_z(data, n);
+    if (!copy)
+      snprintf(err, err_sz, "out of memory");
+    return copy;
+  }
+  if (n >= 4 && memcmp(data, "%PDF", 4) == 0) {
+    int pg = 0;
+    char perr[256];
+    char *text = cst_pdf_text(data, n, &pg, perr, sizeof(perr));
+    if (!text) {
+      snprintf(err, err_sz, "cannot read the PDF: %.200s", perr);
+      return NULL;
+    }
+    snprintf(mime, mime_sz, "application/pdf");
+    *pages = pg;
+    *out_len = strlen(text);
+    return text;
+  }
+  if (n > CST_ATTACH_TEXT_MAX) {
+    snprintf(err, err_sz, "text is %.1f MB; the limit is %d MB",
+             (double)n / (1024 * 1024), (int)(CST_ATTACH_TEXT_MAX >> 20));
+    return NULL;
+  }
+  if (memchr(data, 0, n) || !cst_utf8_valid(data, n)) {
+    snprintf(err, err_sz,
+             "not an image (PNG, JPEG, GIF, WebP or BMP), a PDF or UTF-8 "
+             "text; the content decides, not the extension");
+    return NULL;
+  }
+  snprintf(mime, mime_sz, "text/plain");
+  char *copy = memdup_z(data, n);
+  if (!copy)
+    snprintf(err, err_sz, "out of memory");
+  return copy;
+}
+
+/* Write one payload whose kind is already known. */
 static cst_attachment_t *store(const char *session_path, const char *name,
-                               const char *data, size_t n, const char *origin,
+                               const char *data, size_t n, const char *mime,
-                               char *err, size_t err_sz) {
+                               int pages, const char *origin, char *err,
+                               size_t err_sz) {
   if (!name || !name[0])
     name = "image";
-  char mime[32];
-  if (cst_attach_sniff(data, n, mime, sizeof(mime)) != 0) {
-    snprintf(err, err_sz,
-             "not a supported image (PNG, JPEG, GIF, WebP or BMP; "
-             "checked by content, not by extension)");
-    return NULL;
-  }
-  if (n > CST_ATTACH_MAX_BYTES) {
-    snprintf(err, err_sz, "image is %.1f MB; the limit is %d MB",
-             (double)n / (1024 * 1024), (int)(CST_ATTACH_MAX_BYTES >> 20));
-    return NULL;
-  }
   char dir[OS_PATH_MAX];
   if (cst_attach_dir(session_path, dir, sizeof(dir)) != 0) {
     snprintf(err, err_sz, "cannot create the attachment directory");
@@ -386,7 +440,9 @@ static cst_attachment_t *store(const char *session_path, const char *name,
   snprintf(a->origin, sizeof(a->origin), "%s", origin ? origin : "user");
   snprintf(a->detail, sizeof(a->detail), "auto");
   a->bytes = (long long)n;
-  cst_attach_dimensions(data, n, &a->width, &a->height);
+  a->pages = pages;
+  if (cst_attach_is_image(a))
+    cst_attach_dimensions(data, n, &a->width, &a->height);
 
   char full[OS_PATH_MAX];
   if (cst_attach_full_path(session_path, a, full, sizeof(full)) != 0) {
@@ -419,14 +475,26 @@ cst_attachment_t *cst_attach_import_bytes(const char *session_path,
   }
   err[0] = 0;
   if (!session_path || !session_path[0]) {
-    snprintf(err, err_sz, "no session to store the image in");
+    snprintf(err, err_sz, "no session to store the file in");
     return NULL;
   }
   if (!data || !n) {
-    snprintf(err, err_sz, "image is empty");
+    snprintf(err, err_sz, "the file is empty");
     return NULL;
   }
-  return store(session_path, name, data, n, "user", err, err_sz);
+  char mime[32];
+  if (cst_attach_sniff(data, n, mime, sizeof(mime)) != 0) {
+    snprintf(err, err_sz,
+             "not a supported image (PNG, JPEG, GIF, WebP or BMP; "
+             "checked by content, not by extension)");
+    return NULL;
+  }
+  if (n > CST_ATTACH_MAX_BYTES) {
+    snprintf(err, err_sz, "image is %.1f MB; the limit is %d MB",
+             (double)n / (1024 * 1024), (int)(CST_ATTACH_MAX_BYTES >> 20));
+    return NULL;
+  }
+  return store(session_path, name, data, n, mime, 0, "user", err, err_sz);
 }
 
 cst_attachment_t *cst_attach_import_file(const char *session_path,
@@ -449,11 +517,30 @@ cst_attachment_t *cst_attach_import_file(const char *session_path,
   for (const char *p = src_path; *p; p++)
     if (*p == '/' || *p == '\\')
       leaf = p + 1;
-  cst_attachment_t *a = store(session_path, leaf, data, n, "user", err, err_sz);
+  char mime[32];
+  int pages = 0;
+  size_t pn = 0;
+  char *payload =
+      prepare(data, n, mime, sizeof(mime), &pages, &pn, err, err_sz);
   free(data);
+  if (!payload)
+    return NULL;
+  cst_attachment_t *a =
+      store(session_path, leaf, payload, pn, mime, pages, "user", err, err_sz);
+  free(payload);
   return a;
 }
 
+/* Images are opaque and travel as image parts; everything else is text the
+ * store holds and the request inlines. */
+int cst_attach_is_image(const cst_attachment_t *a) {
+  return a && strncmp(a->mime, "image/", 6) == 0;
+}
+
+int cst_attach_is_text(const cst_attachment_t *a) {
+  return a && !cst_attach_is_image(a);
+}
+
 char *cst_attach_read(const char *session_path, const cst_attachment_t *a,
                       size_t *out_len, char *err, size_t err_sz) {
   char dummy[8];
@@ -470,11 +557,12 @@ char *cst_attach_read(const char *session_path, const cst_attachment_t *a,
   char *data = read_whole(full, out_len, CST_ATTACH_MAX_BYTES);
   if (!data) {
     snprintf(err, err_sz,
-             "%.200s is missing; the image was deleted from the session "
+             "%.200s is missing; it was deleted from the session store",
-             "store",
              a->name);
     return NULL;
   }
+  if (!cst_attach_is_image(a)) /* a document is text, nothing to verify */
+    return data;
   char mime[32];
   if (cst_attach_sniff(data, *out_len, mime, sizeof(mime)) != 0) {
     snprintf(err, err_sz, "%.200s in the session store is no longer an image",
@@ -486,6 +574,8 @@ char *cst_attach_read(const char *session_path, const cst_attachment_t *a,
 }
 
 char *cst_attach_data_url(const char *session_path, const cst_attachment_t *a) {
+  if (!cst_attach_is_image(a)) /* a document travels as text, not as a URL */
+    return NULL;
   char err[256];
   size_t n = 0;
   char *data = cst_attach_read(session_path, a, &n, err, sizeof(err));
@@ -509,10 +599,21 @@ void cst_attach_describe(const cst_attachment_t *a, char *out, size_t out_sz) {
     snprintf(out, out_sz, "(none)");
     return;
   }
-  const char *kind = strncmp(a->mime, "image/", 6) == 0 ? a->mime + 6 : a->mime;
+  const char *kind = a->mime;
   char dim[32] = "";
-  if (a->width > 0 && a->height > 0)
+  if (cst_attach_is_image(a)) {
-    snprintf(dim, sizeof(dim), "%dx%d ", a->width, a->height);
+    if (strncmp(a->mime, "image/", 6) == 0)
+      kind = a->mime + 6;
+    if (a->width > 0 && a->height > 0)
+      snprintf(dim, sizeof(dim), "%dx%d ", a->width, a->height);
+  } else if (strcmp(a->mime, "application/pdf") == 0) {
+    kind = "pdf";
+    if (a->pages > 0)
+      snprintf(dim, sizeof(dim), "%d page%s ", a->pages,
+               a->pages == 1 ? "" : "s");
+  } else if (strcmp(a->mime, "text/plain") == 0 || !a->mime[0]) {
+    kind = "text";
+  }
   out[0] = 0;
   if (a->bytes >= 1024 * 1024)
     snprintf(out, out_sz, "%s%s %.1f MB", dim, kind,
@@ -580,6 +681,8 @@ char *cst_attachments_to_json(const cst_attachment_t *list, int n) {
       cJSON_AddNumberToObject(o, "width", a->width);
       cJSON_AddNumberToObject(o, "height", a->height);
     }
+    if (a->pages > 0)
+      cJSON_AddNumberToObject(o, "pages", a->pages);
     if (a->detail[0] && strcmp(a->detail, "auto") != 0)
       cJSON_AddStringToObject(o, "detail", a->detail);
     if (a->origin[0])
@@ -628,6 +731,8 @@ cst_attachment_t *cst_attachments_from_json(const void *array_json, int *n_out)
     a->width = cJSON_IsNumber(v) ? v->valueint : 0;
     v = cJSON_GetObjectItemCaseSensitive(it, "height");
     a->height = cJSON_IsNumber(v) ? v->valueint : 0;
+    v = cJSON_GetObjectItemCaseSensitive(it, "pages");
+    a->pages = cJSON_IsNumber(v) ? v->valueint : 0;
     v = cJSON_GetObjectItemCaseSensitive(it, "detail");
     snprintf(a->detail, sizeof(a->detail), "%s",
              cJSON_IsString(v) ? v->valuestring : "auto");

src/clipboard.c

@@ -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';

src/llm_openai.c

@@ -255,28 +255,78 @@ static cJSON *image_part(const cst_llm_request_t *req,
   return p;
 }
 
-/* Append every attachment of m as image parts (or a note saying why not). */
+/* One stored document as a text part: its text, framed so the model knows
-static void parts_add_images(const cst_llm_request_t *req, cJSON *parts,
+ * where it came from. Documents are plain text on the wire, so a text-only
-                             const cst_message_t *m, size_t *budget) {
+ * model and CST_NO_IMAGES both still get them. */
+static cJSON *document_part(const cst_llm_request_t *req,
+                            const cst_attachment_t *a, size_t *budget,
+                            char *why, size_t why_sz) {
+  why[0] = 0;
+  if (!req->session_path || !req->session_path[0]) {
+    snprintf(why, why_sz, "there is no session store to read it from");
+    return NULL;
+  }
+  char err[256];
+  size_t n = 0;
+  char *text = cst_attach_read(req->session_path, a, &n, err, sizeof(err));
+  if (!text) {
+    snprintf(why, why_sz, "%s", err);
+    return NULL;
+  }
+  int cut = 0;
+  if (n > *budget) {
+    n = *budget;
+    cut = 1;
+  }
+  *budget -= n;
+  char desc[128];
+  cst_attach_describe(a, desc, sizeof(desc));
+  cst_buf_t b = {0};
+  cst_buf_printf(&b, "[document \"%.120s\" (%s)%s]\n", a->name, desc,
+                 cut ? " -- only the start is included" : "");
+  cst_buf_append(&b, text, n);
+  cst_buf_puts(&b, cut ? "\n[-- document truncated --]"
+                       : "\n[-- end of document --]");
+  free(text);
+  cJSON *p = cJSON_CreateObject();
+  cJSON_AddStringToObject(p, "type", "text");
+  cJSON_AddStringToObject(p, "text", b.buf ? b.buf : "");
+  cst_buf_free(&b);
+  return p;
+}
+
+/* Append every attachment of m: images as image parts (or a note saying why
+ * not), documents inline as text. */
+static void parts_add_attachments(const cst_llm_request_t *req, cJSON *parts,
+                                  const cst_message_t *m, size_t *budget,
+                                  size_t *doc_budget, const char *img_off) {
   int n = m->nattach;
   if (n > CST_ATTACH_MAX_COUNT) {
     char note[160];
-    snprintf(note, sizeof(note), "[%d of %d images sent]", CST_ATTACH_MAX_COUNT,
+    snprintf(note, sizeof(note),
-             n);
+             "[only the first %d of %d attachments are sent]",
+             CST_ATTACH_MAX_COUNT, n);
     parts_add_text(parts, cJSON_CreateString(note));
     n = CST_ATTACH_MAX_COUNT;
   }
   for (int i = 0; i < n; i++) {
     const cst_attachment_t *a = &m->attach[i];
+    int is_img = cst_attach_is_image(a);
     char why[256];
-    cJSON *p = image_part(req, a, budget, why, sizeof(why));
+    cJSON *p = NULL;
+    if (is_img && img_off)
+      snprintf(why, sizeof(why), "%s", img_off);
+    else if (is_img)
+      p = image_part(req, a, budget, why, sizeof(why));
+    else
+      p = document_part(req, a, doc_budget, why, sizeof(why));
     if (p) {
       cJSON_AddItemToArray(parts, p);
       continue;
     }
     char note[512];
-    snprintf(note, sizeof(note), "[image \"%.120s\" not sent: %.200s]",
+    snprintf(note, sizeof(note), "[%s \"%.120s\" not sent: %.200s]",
-             a->name, why);
+             is_img ? "image" : "document", a->name, why);
     parts_add_text(parts, cJSON_CreateString(note));
   }
 }
@@ -284,8 +334,10 @@ static void parts_add_images(const cst_llm_request_t *req, cJSON *parts,
 /* Images a tool result produced are deferred: an assistant tool_call must be
  * answered by tool messages only, so they ride in one extra user message
  * after the run of tool messages ends. *pending collects it. */
-static void defer_images(const cst_llm_request_t *req, const cst_message_t *m,
+static void defer_attachments(const cst_llm_request_t *req,
-                         cJSON **pending, size_t *budget) {
+                              const cst_message_t *m, cJSON **pending,
+                              size_t *budget, size_t *doc_budget,
+                              const char *img_off) {
   cJSON *p = *pending;
   if (!p) {
     p = cJSON_CreateObject();
@@ -293,15 +345,18 @@ static void defer_images(const cst_llm_request_t *req, const cst_message_t *m,
     cJSON_AddArrayToObject(p, "content");
     *pending = p;
   }
-  parts_add_images(req, cJSON_GetObjectItemCaseSensitive(p, "content"), m,
+  parts_add_attachments(req, cJSON_GetObjectItemCaseSensitive(p, "content"), m,
-                   budget);
+                        budget, doc_budget, img_off);
 }
 
-/* m's text plus one line per image it would have carried (malloc'd). */
+/* m's text plus one line per image it would have carried (malloc'd); a
+ * document is not affected (it is text and is sent as such). */
 static char *image_notes(const cst_message_t *m, const char *why) {
   cst_buf_t b = {0};
   cst_buf_puts(&b, m->content ? m->content : "");
   for (int i = 0; i < m->nattach; i++) {
+    if (!cst_attach_is_image(&m->attach[i]))
+      continue;
     char d[128];
     cst_attach_describe(&m->attach[i], d, sizeof(d));
     cst_buf_printf(&b, "%s[image \"%.120s\" (%s) not sent: %s]",
@@ -394,6 +449,7 @@ char *cst_llm_build_body(const cst_llm_request_t *req) {
   cJSON *prev_user = NULL; /* merge consecutive user messages */
   cJSON *pending = NULL;   /* images from tool results, waiting for a break */
   size_t img_budget = CST_ATTACH_MAX_TOTAL;
+  size_t doc_budget = CST_ATTACH_MAX_TOTAL;
   const char *noimg = getenv("CST_NO_IMAGES");
   const char *img_off =
       noimg && noimg[0] && noimg[0] != '0'
@@ -407,15 +463,26 @@ char *cst_llm_build_body(const cst_llm_request_t *req) {
     cst_role_t role = m->role;
     if (role == CST_ROLE_TOOL && !m->tool_call_id[0])
       role = CST_ROLE_USER;
-    int has_img = m->attach && m->nattach > 0;
+    int n_att = m->attach ? m->nattach : 0;
+    int has_img = 0, has_doc = 0;
+    for (int k = 0; k < n_att; k++) {
+      if (cst_attach_is_image(&m->attach[k]))
+        has_img = 1;
+      else
+        has_doc = 1;
+    }
     char *noted = NULL;
     if (has_img && img_off) {
-      /* plain text: text-only APIs may refuse content arrays */
-      noted = image_notes(m, img_off);
-      if (noted)
-        mm.content = noted;
       has_img = 0;
+      if (!has_doc) {
+        /* plain text: text-only APIs may refuse content arrays */
+        noted = image_notes(m, img_off);
+        if (noted)
+          mm.content = noted;
+      }
     }
+    /* a document needs a content array even when no image can go out */
+    int att_parts = has_img || has_doc;
 
     /* Every tool_call must be answered by tool messages, so tool-produced
      * images only leave the queue when the run of tool results is over. */
@@ -431,7 +498,7 @@ char *cst_llm_build_body(const cst_llm_request_t *req) {
       cJSON *pc = prev_user
                       ? cJSON_GetObjectItemCaseSensitive(prev_user, "content")
                       : NULL;
-      if (!has_img && !cJSON_IsArray(pc)) {
+      if (!att_parts && !cJSON_IsArray(pc)) {
         cJSON *c = clean_string(m->content, 0);
         if (prev_user) {
           cst_buf_t b = {0};
@@ -463,8 +530,8 @@ char *cst_llm_build_body(const cst_llm_request_t *req) {
       }
       cJSON *parts = content_parts(o);
       parts_add_text(parts, clean_string(m->content, 0));
-      if (has_img)
+      if (att_parts)
-        parts_add_images(req, parts, m, &img_budget);
+        parts_add_attachments(req, parts, m, &img_budget, &doc_budget, img_off);
       free(noted);
       continue;
     }
@@ -498,8 +565,8 @@ char *cst_llm_build_body(const cst_llm_request_t *req) {
         cJSON_AddTrueToObject(o, "prefix");
     }
     cJSON_AddItemToArray(msgs, o);
-    if (role == CST_ROLE_TOOL && has_img)
+    if (role == CST_ROLE_TOOL && n_att)
-      defer_images(req, m, &pending, &img_budget);
+      defer_attachments(req, m, &pending, &img_budget, &doc_budget, img_off);
     free(noted);
   }
   if (pending)

src/main.c

@@ -26,6 +26,8 @@ static void usage(const char *argv0) {
           "                        (last used)\n"
           "  -m, --model NAME      model (last used for the provider)\n"
           "  -e, --effort LEVEL    low | medium | high | max (last used)\n"
+          "  -M, --mode NAME       coding (default, code framed) | general\n"
+          "                        (documents, data, research; last used)\n"
           "  -w, --workspace DIR   project directory (default: current)\n"
           "  -c, --continue        reopen the last session (default)\n"
           "  -N, --new             start a new session\n"
@@ -59,13 +61,13 @@ static void usage(const char *argv0) {
           "API keys: the TUI asks for a missing key and saves it per provider\n"
           "  in the config dir (credentials, mode 0600); /key changes it.\n"
           "  Fallbacks: <provider env> (DEEPSEEK_API_KEY, ...), CST_API_KEY.\n"
-          "Settings: provider, models and effort are remembered in\n"
+          "Settings: provider, models, effort and mode are remembered in\n"
           "  settings.json next to the credentials.\n"
-          "Env:  CST_PROVIDER CST_MODEL CST_EFFORT CST_PROTOCOL CST_TOOLS\n"
+          "Env:  CST_PROVIDER CST_MODEL CST_EFFORT CST_MODE CST_PROTOCOL\n"
-          "      CST_CONFIRM CST_MAX_STEPS CST_TOOL_OUT_CAP CST_CTX_WINDOW\n"
+          "      CST_TOOLS CST_CONFIRM CST_MAX_STEPS CST_TOOL_OUT_CAP\n"
-          "      CST_CTX_TOKENS CST_AUTO_COMPACT=0 CST_SHELL_TIMEOUT\n"
+          "      CST_CTX_WINDOW CST_CTX_TOKENS CST_AUTO_COMPACT=0\n"
-          "      CST_METRICS=0 CST_RECORD_SSE CST_REPLAY_SSE CST_MODELS\n"
+          "      CST_SHELL_TIMEOUT CST_METRICS=0 CST_RECORD_SSE CST_REPLAY_SSE\n"
-          "      CST_APPROVAL=ask|auto|yolo CST_AUTO_APPROVE=1 (=yolo)\n"
+          "      CST_MODELS CST_APPROVAL=ask|auto|yolo CST_AUTO_APPROVE=1 (=yolo)\n"
           "      CST_SANDBOX=off CST_SHELL CST_NO_PROJECT_NOTES=1 NO_COLOR\n"
           "TUI: type /help inside for commands and keys\n",
           argv0);
@@ -374,6 +376,7 @@ int main(int argc, char **argv) {
       {"approval", required_argument, 0, 'A'},
       {"confirm", required_argument, 0, 'C'},
       {"effort", required_argument, 0, 'e'},
+      {"mode", required_argument, 0, 'M'},
       {"help", no_argument, 0, 'h'},
       {"version", no_argument, 0, 'V'},
       {"list-models", optional_argument, 0, 0x100},
@@ -385,8 +388,8 @@ int main(int argc, char **argv) {
       {"web-open", no_argument, 0, 0x106},
       {0, 0, 0, 0}};
   int c;
-  while ((c = getopt_long(argc, argv, "w:s:b:k:m:P:r:n:T:Hp:dahVNcR:LyA:C:e:", opts, NULL)) !=
+  while ((c = getopt_long(argc, argv, "w:s:b:k:m:P:r:n:T:Hp:dahVNcR:LyA:C:e:M:",
-         -1) {
+                          opts, NULL)) != -1) {
     switch (c) {
     case 'w':
       snprintf(cfg.workspace_root, sizeof(cfg.workspace_root), "%s", optarg);
@@ -478,6 +481,14 @@ int main(int argc, char **argv) {
       }
       snprintf(cfg.effort, sizeof(cfg.effort), "%s", optarg);
       break;
+    case 'M':
+      if (!cst_mode_valid(optarg)) {
+        fprintf(stderr, "bad --mode %s (coding | general)\n", optarg);
+        curl_global_cleanup();
+        return 1;
+      }
+      snprintf(cfg.mode, sizeof(cfg.mode), "%s", optarg);
+      break;
     case 'h':
       usage(argv[0]);
       curl_global_cleanup();
@@ -557,6 +568,12 @@ int main(int argc, char **argv) {
     snprintf(cfg.effort, sizeof(cfg.effort), "%s",
              cst_effort_valid(e) ? e : CST_DEFAULT_EFFORT);
   }
+  if (!cfg.mode[0]) {
+    const char *m = getenv("CST_MODE");
+    if (!cst_mode_valid(m))
+      m = saved.mode;
+    snprintf(cfg.mode, sizeof(cfg.mode), "%s", cst_mode_name(m));
+  }
   if (!cfg.api_base[0]) {
     const char *env_base = getenv("CST_API_BASE");
     if (!env_base || !env_base[0])

src/session.c

@@ -452,7 +452,10 @@ char *cst_session_export_md(cst_session_t *s, const char *title,
       for (int k = 0; k < m->nattach; k++) {
         char d[128];
         cst_attach_describe(&m->attach[k], d, sizeof(d));
-        cst_buf_printf(&b, "- image `%s` (%s)\n", m->attach[k].name, d);
+        cst_buf_printf(&b, "- %s `%s` (%s)\n",
+                       cst_attach_is_image(&m->attach[k]) ? "image"
+                                                         : "document",
+                       m->attach[k].name, d);
       }
       if (m->nattach)
         cst_buf_puts(&b, "\n");

src/settings.c

@@ -47,6 +47,8 @@ int cst_settings_load(cst_settings_t *s) {
            cJSON_GetObjectItemCaseSensitive(root, "provider"));
   copy_str(s->effort, sizeof(s->effort),
            cJSON_GetObjectItemCaseSensitive(root, "effort"));
+  copy_str(s->mode, sizeof(s->mode),
+           cJSON_GetObjectItemCaseSensitive(root, "mode"));
   copy_str(s->approval, sizeof(s->approval),
            cJSON_GetObjectItemCaseSensitive(root, "approval"));
   s->show_thinking =
@@ -86,6 +88,8 @@ int cst_settings_save(const cst_settings_t *s) {
     cJSON_AddStringToObject(root, "provider", s->provider);
   if (s->effort[0])
     cJSON_AddStringToObject(root, "effort", s->effort);
+  if (s->mode[0])
+    cJSON_AddStringToObject(root, "mode", s->mode);
   if (s->approval[0])
     cJSON_AddStringToObject(root, "approval", s->approval);
   if (s->show_thinking)
@@ -135,6 +139,21 @@ int cst_approval_parse(const char *s, int *out) {
   return -1;
 }
 
+static const char *const MODE_NAMES[] = {"coding", "general"};
+
+int cst_mode_valid(const char *m) {
+  for (size_t i = 0; m && m[0] && i < sizeof(MODE_NAMES) / sizeof(*MODE_NAMES);
+       i++) {
+    if (strcmp(m, MODE_NAMES[i]) == 0)
+      return 1;
+  }
+  return 0;
+}
+
+const char *cst_mode_name(const char *m) {
+  return cst_mode_valid(m) ? m : CST_DEFAULT_MODE;
+}
+
 const char *cst_settings_model(const cst_settings_t *s, const char *provider) {
   for (int i = 0; provider && i < s->nmodels; i++) {
     if (strcmp(s->models[i].provider, provider) == 0 && s->models[i].model[0])
@@ -148,6 +167,8 @@ int cst_settings_remember(const cst_agent_config_t *cfg) {
   cst_settings_load(&s);
   snprintf(s.provider, sizeof(s.provider), "%s", cfg->provider);
   snprintf(s.effort, sizeof(s.effort), "%s", cfg->effort);
+  if (cfg->mode[0])
+    snprintf(s.mode, sizeof(s.mode), "%s", cfg->mode);
   int i = 0;
   while (i < s.nmodels && strcmp(s.models[i].provider, cfg->provider) != 0)
     i++;
@@ -176,6 +197,13 @@ int cst_settings_remember_thinking(int show_thinking) {
   return cst_settings_save(&s);
 }
 
+int cst_settings_remember_mode(const char *mode) {
+  cst_settings_t s;
+  cst_settings_load(&s);
+  snprintf(s.mode, sizeof(s.mode), "%s", cst_mode_name(mode));
+  return cst_settings_save(&s);
+}
+
 static void real_ws(const char *ws, char *out, size_t n) {
   if (!ws || os_realpath(ws, out, n) != 0)
     snprintf(out, n, "%s", ws ? ws : "");

src/subagent.c

@@ -40,7 +40,7 @@ static const struct {
      "runs commands as needed.",
      "", 0},
     {"explore",
-     "Fast read-only explorer: searches and reads the codebase to answer a "
+     "Fast read-only explorer: searches and reads the workspace to answer a "
      "question (where is X, how does Y work, which files do Z). Several can "
      "run at once.",
      "You only read. Search broadly first (grep, glob, list_dir), then read "
@@ -49,11 +49,11 @@ static const struct {
      "you looked for and did not find.",
      1},
     {"plan",
-     "Read-only planner: investigates the code involved and returns a "
+     "Read-only planner: investigates the material involved and returns a "
      "step-by-step implementation plan.",
-     "You only read. Investigate the code involved, then return a concrete "
+     "You only read. Investigate what is involved, then return a concrete "
-     "plan: the files to change and what to change in each, risks and edge "
+     "plan: what to produce or change and where, risks and edge cases, and "
-     "cases, and how to verify. Sketch code only where it removes ambiguity.",
+     "how to check the result. Sketch code only where it removes ambiguity.",
      1},
 };
 #define NBUILTIN ((int)(sizeof(BUILTIN) / sizeof(BUILTIN[0])))

src/tools/agent_tools.c

@@ -7,6 +7,7 @@
 #include <string.h>
 
 #include "cst_tools.h"
+#include "cst_clipboard.h"
 #include "cst_util.h"
 #include "tools_internal.h"
 
@@ -106,3 +107,70 @@ int cst_tool_ask_user(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
                            1);
   return tool_set_resultf(r, 0, "user answered: %s", ans);
 }
+
+/* The system clipboard: what the user copied elsewhere. Reading needs no
+ * permission (READ); writing replaces what the user has copied (WRITE, so
+ * the confirmation frontier applies). */
+int cst_tool_clipboard_read(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
+                            cst_tool_result_t *r) {
+  (void)ctx;
+  char err[192];
+  char *text = NULL;
+  size_t n = 0;
+  if (cst_clipboard_text(&text, &n, err, sizeof(err)) != 0)
+    return tool_set_result(r, err, 1);
+  long cap = tool_arg_long(c, "max_bytes", 65536);
+  if (cap > 0 && (size_t)cap < n)
+    n = (size_t)cap;
+  cst_buf_t b = {0};
+  cst_buf_printf(&b, "clipboard text (%zu bytes%s):\n", (size_t)n,
+                 (size_t)cap < (size_t)n ? ", truncated" : "");
+  cst_buf_append(&b, text, n);
+  if (b.len && b.buf[b.len - 1] != '\n')
+    cst_buf_puts(&b, "\n");
+  free(text);
+  return tool_take_buf(r, &b, 0);
+}
+
+int cst_tool_clipboard_write(const cst_tool_ctx_t *ctx,
+                             const ctl_tool_call_t *c, cst_tool_result_t *r) {
+  (void)ctx;
+  size_t n = 0;
+  const char *text = tool_arg_n(c, "text", &n);
+  if (!text)
+    return tool_set_result(r, "error: missing text", 1);
+  char err[192];
+  if (cst_clipboard_set_text(text, n, err, sizeof(err)) != 0)
+    return tool_set_result(r, err, 1);
+  return tool_set_resultf(r, 0, "copied %zu bytes to the clipboard", n);
+}
+
+/* Confirmation preview: what the clipboard would hold afterwards. Clipboard
+ * text has no diff, so this is the text itself, cut to a readable size. */
+#define CLIP_PREVIEW_MAX 2000
+int cst_preview_clipboard_write(const cst_tool_ctx_t *ctx,
+                                const ctl_tool_call_t *c, char **out) {
+  (void)ctx;
+  size_t n = 0;
+  const char *text = tool_arg_n(c, "text", &n);
+  if (!text) {
+    *out = strdup("error: missing text");
+    return -1;
+  }
+  int lines = 0;
+  for (size_t i = 0; i < n; i++)
+    lines += text[i] == '\n';
+  size_t cut = n;
+  if (cut > CLIP_PREVIEW_MAX)
+    cut = cst_utf8_floor(text, CLIP_PREVIEW_MAX);
+  cst_buf_t b = {0};
+  cst_buf_printf(&b, "clipboard: replace with %zu bytes, %d line%s\n", n,
+                 lines + (n && text[n - 1] != '\n'), lines == 0 ? "" : "s");
+  cst_buf_append(&b, text, cut);
+  if (b.len && b.buf[b.len - 1] != '\n')
+    cst_buf_puts(&b, "\n");
+  if (cut < n)
+    cst_buf_printf(&b, "… (%zu more bytes)\n", n - cut);
+  *out = cst_buf_steal(&b);
+  return 0;
+}

src/tools/fs_tools.c

@@ -267,6 +267,14 @@ int cst_tool_view_image(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
   cst_attachment_t *a = cst_attach_import_file(session, full, err, sizeof(err));
   if (!a)
     return tool_set_resultf(r, 1, "error: cannot show %.200s: %s", path, err);
+  if (!cst_attach_is_image(a)) {
+    cst_attach_free(a);
+    return tool_set_resultf(
+        r, 1,
+        "error: %.200s is not an image; a text file or PDF reaches the model "
+        "through /attach <path> (a PDF becomes its text layer)",
+        path);
+  }
   snprintf(a->origin, sizeof(a->origin), "view_image");
   const char *d = tool_arg(c, "detail");
   if (d && (strcmp(d, "low") == 0 || strcmp(d, "high") == 0))

src/tools/registry.c

@@ -66,8 +66,9 @@ static const cst_tool_def_t TOOLS[] = {
       {"detail", S, 0, "low or high (provider hint; default auto)"}},
      CST_TP_READ, 0, cst_tool_view_image, NULL, NO_DYN},
     {"run_shell",
-     "Run a non-interactive shell command in the workspace root for builds, "
+     "Run a non-interactive shell command in the workspace root: builds, "
-     "tests, git and other CLIs (stdin is empty; long runs are killed). "
+     "tests, git, scripts, computations, data processing, other CLIs "
+     "(stdin is empty; long runs are killed). "
      "Returns stdout+stderr with colors stripped and long output cut to head "
      "+ tail. Prefer read_file/grep/glob/list_dir over cat/grep/find.",
      "Run a shell command in the workspace root (non-interactive, stdin is "
@@ -158,6 +159,19 @@ static const cst_tool_def_t TOOLS[] = {
      {{"question", S, 1, "the question"},
       {"options", S, 0, "suggested answers, one per line"}},
      CST_TP_ASK, 0, cst_tool_ask_user, NULL, NO_DYN},
+    {"clipboard_read",
+     "Read the text on the system clipboard — what the user copied outside "
+     "the workspace. Returns UTF-8 text.",
+     NULL,
+     {{"max_bytes", I, 0, "cap on the returned text (default 65536)"}},
+     CST_TP_READ, 0, cst_tool_clipboard_read, NULL, NO_DYN},
+    {"clipboard_write",
+     "Replace the system clipboard with text, so the user can paste it into "
+     "another app. Overwrites what they had copied.",
+     NULL,
+     {{"text", S, 1, "text to put on the clipboard"}},
+     CST_TP_WRITE, 0, cst_tool_clipboard_write, cst_preview_clipboard_write,
+     NO_DYN},
 };
 #define NTOOLS ((int)(sizeof(TOOLS) / sizeof(TOOLS[0])))
 

src/tools/tools_internal.h

@@ -46,6 +46,13 @@ int cst_tool_todo_write(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
                         cst_tool_result_t *r);
 int cst_tool_ask_user(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
                       cst_tool_result_t *r);
+/* Clipboard text (system clipboard, not the workspace). */
+int cst_tool_clipboard_read(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
+                            cst_tool_result_t *r);
+int cst_tool_clipboard_write(const cst_tool_ctx_t *ctx,
+                             const ctl_tool_call_t *c, cst_tool_result_t *r);
+int cst_preview_clipboard_write(const cst_tool_ctx_t *ctx,
+                                const ctl_tool_call_t *c, char **out);
 int cst_tool_web_fetch(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
                        cst_tool_result_t *r);
 int cst_tool_view_image(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,

src/tui.c

@@ -2354,6 +2354,7 @@ static const char *const TIPS[] = {
     "Ctrl+P opens the command palette",
     "Type @ to mention a file in your message",
     "/effort sets reasoning effort: low, medium, high, max",
+    "/mode general reframes the agent for non-code work",
     "/model lists the models your API key can use",
     "/undo reverts the file changes of the last turn",
     "/provider switches provider; keys are saved per provider",
@@ -2832,7 +2833,10 @@ static void reload_hist_from_session(tui_t *t) {
       for (int k = 0; k < m->nattach; k++) {
         char d[128];
         cst_attach_describe(&m->attach[k], d, sizeof(d));
-        cst_buf_printf(&ub, "\n[image %s · %s]", m->attach[k].name, d);
+        cst_buf_printf(&ub, "\n[%s %s · %s]",
+                       cst_attach_is_image(&m->attach[k]) ? "image"
+                                                          : "document",
+                       m->attach[k].name, d);
       }
       block_set_body(b, ub.buf ? ub.buf : "", ub.len);
       cst_buf_free(&ub);
@@ -4361,6 +4365,41 @@ static void cmd_effort(tui_t *t, char *arg, int *quit) {
                      cfg->effort, cfg->provider, cfg->model);
 }
 
+static void cmd_mode(tui_t *t, char *arg, int *quit) {
+  (void)quit;
+  cst_agent_config_t *cfg = cst_agent_config_mut(t->agent);
+  static const char *const names[] = {"coding", "general"};
+  static const char *const desc[] = {
+      "code framed: repo, build, tests (default)",
+      "documents, data, research, everyday files"};
+  const char *want = NULL;
+  if (arg && arg[0]) {
+    if (!cst_mode_valid(arg)) {
+      push_system_line(t, "Unknown mode '%s' (coding | general)", arg);
+      return;
+    }
+    want = arg;
+  } else {
+    char items[2][128];
+    int cur_idx = 0;
+    for (int i = 0; i < 2; i++) {
+      snprintf(items[i], 128, "%-8s %s", names[i], desc[i]);
+      if (strcmp(names[i], cst_mode_name(cfg->mode)) == 0)
+        cur_idx = i;
+    }
+    int pick = picker_run(t, "Working mode", items, 2, cur_idx);
+    if (pick < 0)
+      return;
+    want = names[pick];
+  }
+  snprintf(cfg->mode, sizeof(cfg->mode), "%s", want);
+  cst_settings_remember_mode(cfg->mode);
+  push_system_line(t, "(mode → %s%s)", cfg->mode,
+                   strcmp(cfg->mode, "general") == 0
+                       ? "; the system prompt is rewritten on the next turn"
+                       : "");
+}
+
 static void cmd_provider(tui_t *t, char *arg, int *quit) {
   (void)quit;
   cst_agent_config_t *cfg = cst_agent_config_mut(t->agent);
@@ -4639,14 +4678,15 @@ static void cmd_status(tui_t *t, char *arg, int *quit) {
                    : !same          ? "this run only (--api-key / CST_API_KEY)"
                    : strcmp(from, "saved") == 0 ? "saved (/key to replace)"
                                                 : from);
-  push_system_line(t, "  protocol   %s · tools %s · max steps %d",
+  push_system_line(t, "  protocol   %s · tools %s · mode %s · max steps %d",
                    cst_protocol_name(cfg->protocol),
-                   cst_tool_profile_name(cfg->tool_profile), cfg->max_steps);
+                   cst_tool_profile_name(cfg->tool_profile),
+                   cst_mode_name(cfg->mode), cfg->max_steps);
   char appr[64];
   approval_label(t, appr, sizeof(appr));
   push_system_line(t, "  approval   %s — %s", appr,
                    approval_help(approval_mode(t)));
-  push_system_line(t, "  mode       %s",
+  push_system_line(t, "  plan       %s",
                    cfg->plan_mode ? "Plan (read-only tools)" : "Build");
   const char *notes = cst_agent_notes(t->agent);
   push_system_line(t, "  notes      %s",
@@ -4825,19 +4865,39 @@ static void report_attached(tui_t *t, int added) {
                      cst_agent_config(t->agent)->model);
 }
 
-/* /attach: stage images for the next user message. The bytes are copied into
+/* /attach paste: the clipboard image if there is one, else its text goes
- * the session's attachment directory now, so a picture picked from /tmp keeps
+ * into the composer (CR dropped, control bytes kept out, INPUT_CAP respected). */
- * working after the file is gone. */
+static int paste_text_into_input(tui_t *t, const char *text, size_t n) {
+  char *buf = malloc(n + 1);
+  if (!buf)
+    return 0;
+  size_t k = 0;
+  for (size_t i = 0; i < n && t->in_len + k + 1 < INPUT_CAP; i++) {
+    unsigned char c = (unsigned char)text[i];
+    if (c == '\r' || (c < 0x20 && c != '\n' && c != '\t'))
+      continue;
+    buf[k++] = (char)c;
+  }
+  if (k)
+    input_insert(t, buf, k);
+  free(buf);
+  return (int)k;
+}
+
+/* /attach: stage files for the next user message -- images, PDFs (reduced to
+ * their text) and text. The payload is copied into the session's attachment
+ * directory now, so a file picked from /tmp keeps working after it is gone. */
 static void cmd_attach(tui_t *t, char *arg, int *quit) {
   (void)quit;
   int n = cst_agent_pending_count(t->agent);
   if (!arg || !arg[0] || strcmp(arg, "list") == 0) {
     if (n == 0) {
-      push_system_line(t, "No images picked. Usage: /attach <path>");
+      push_system_line(t, "Nothing attached yet. Usage: /attach <path>, "
+                          "/attach paste, /attach list, /attach clear");
       return;
     }
-    push_system_line(t, "%d image%s with the next message (sent once):", n,
+    push_system_line(t, "%d attachment%s with the next message (sent once):",
-                     n > 1 ? "s" : "");
+                     n, n > 1 ? "s" : "");
     for (int i = 0; i < n; i++) {
       char line[256];
       if (cst_agent_pending_describe(t->agent, i, line, sizeof(line)) == 0)
@@ -4848,7 +4908,7 @@ static void cmd_attach(tui_t *t, char *arg, int *quit) {
   }
   if (strcmp(arg, "clear") == 0 || strcmp(arg, "none") == 0) {
     cst_agent_pending_clear(t->agent);
-    push_system_line(t, "Dropped the picked images.");
+    push_system_line(t, "Dropped the attachments.");
     return;
   }
   char err[256];
@@ -4856,7 +4916,24 @@ static void cmd_attach(tui_t *t, char *arg, int *quit) {
     char *img = NULL;
     size_t len = 0;
     if (cst_clipboard_image(&img, &len, err, sizeof(err)) != 0) {
-      push_system_line(t, "Error: %s", err);
+      /* no image: put the clipboard text in the composer instead */
+      char *text = NULL;
+      size_t tn = 0;
+      char terr[192];
+      if (cst_clipboard_text(&text, &tn, terr, sizeof(terr)) != 0) {
+        push_system_line(t, "Error: %s", terr);
+        return;
+      }
+      int added = paste_text_into_input(t, text, tn);
+      free(text);
+      if (added <= 0) {
+        push_system_line(t, "(no room in the composer for the clipboard "
+                            "text)");
+        return;
+      }
+      push_system_line(t, "(pasted %d bytes of clipboard text into the "
+                          "composer)", added);
+      layout_maybe_grow_input(t);
       return;
     }
     char mime[32], name[32];
@@ -4881,19 +4958,29 @@ static void cmd_attach(tui_t *t, char *arg, int *quit) {
   report_attached(t, 1);
 }
 
-static int file_is_image(const char *path) {
+/* A file worth attaching: an image, a PDF, or something that reads as text.
+ * Deciding here in the TUI only avoids turning a random dropped binary into
+ * a pasted path; the store checks the content for real. */
+static int file_is_attachable(const char *path) {
   FILE *f = fopen(path, "rb");
   if (!f)
     return 0;
-  unsigned char head[16];
+  unsigned char head[64];
   size_t got = fread(head, 1, sizeof(head), f);
   fclose(f);
   char mime[32];
-  return cst_attach_sniff(head, got, mime, sizeof(mime)) == 0;
+  if (cst_attach_sniff(head, got, mime, sizeof(mime)) == 0)
+    return 1;
+  if (got >= 4 && memcmp(head, "%PDF", 4) == 0)
+    return 1;
+  for (size_t i = 0; i < got; i++)
+    if (head[i] == 0 || head[i] < 0x09)
+      return 0;
+  return got > 0;
 }
 
-/* A paste that is nothing but image file paths (a file dropped on the
+/* A paste that is nothing but file paths (a file dropped on the terminal)
- * terminal) attaches those files instead of typing the paths. */
+ * attaches those files instead of typing the paths. */
 static void paste_image_paths(tui_t *t) {
   size_t from = t->paste_at, to = t->cur;
   if (to <= from || to - from != t->in_len - t->paste_len0 ||
@@ -4905,7 +4992,7 @@ static void paste_image_paths(tui_t *t) {
   if (n <= 0)
     return;
   for (int i = 0; i < n; i++)
-    if (!file_is_image(paths[i]))
+    if (!file_is_attachable(paths[i]))
       return;
   input_erase(t, from, to);
   int added = 0;
@@ -5441,6 +5528,8 @@ static const slash_cmd_t SLASH[] = {
      cmd_protocol},
     {"tools", "", "[on|off NAME|minimal]", "list or toggle tools", 0,
      cmd_tools},
+    {"mode", "", "[coding|general]", "coding or general (non-code) framing", 1,
+     cmd_mode},
     {"permissions", "perms", "[reset]", "show saved always-allow rules", 1,
      cmd_permissions},
     {"sandbox", "", "[reset-labels]", "shell sandbox and labeled folders", 1,
@@ -5464,8 +5553,8 @@ static const slash_cmd_t SLASH[] = {
     {"export", "", "[file]", "write the transcript as Markdown", 1,
      cmd_export},
     {"copy", "", "", "copy the last reply (OSC 52)", 1, cmd_copy},
-    {"attach", "image", "[path|paste|clear]",
+    {"attach", "image|file", "[path|paste|clear]",
-     "send image(s) with the next message",
+     "send files (image, PDF, text) or clipboard text with the next message",
      1, cmd_attach},
     {"init", "", "", "have the agent write AGENTS.md", 0, cmd_init},
     {"details", "", "", "expand/collapse all tool output", 1, cmd_details},

src/webui.c

@@ -263,6 +263,7 @@ static cJSON *wui_state_new(wui_t *w) {
   cJSON_AddStringToObject(o, "provider", cfg->provider);
   cJSON_AddStringToObject(o, "model", cfg->model);
   cJSON_AddStringToObject(o, "effort", cfg->effort);
+  cJSON_AddStringToObject(o, "mode", cst_mode_name(cfg->mode));
   cJSON_AddStringToObject(o, "approval", cst_approval_name(cfg->approval));
   cJSON_AddStringToObject(o, "protocol_tools", cst_protocol_name(cfg->protocol));
   cJSON_AddBoolToObject(o, "plan_mode", cfg->plan_mode);
@@ -1670,6 +1671,12 @@ static int h_settings_get(cst_http_conn_t *c, void *ud) {
   cJSON *pr = cJSON_AddArrayToObject(o, "profiles");
   for (int p = CST_TOOLS_DEFAULT; pr && p <= CST_TOOLS_MINIMAL; p++)
     cJSON_AddItemToArray(pr, cJSON_CreateString(cst_tool_profile_name(p)));
+  cJSON_AddStringToObject(o, "mode", cst_mode_name(cfg->mode));
+  cJSON *md = cJSON_AddArrayToObject(o, "modes");
+  if (md) {
+    cJSON_AddItemToArray(md, cJSON_CreateString("coding"));
+    cJSON_AddItemToArray(md, cJSON_CreateString("general"));
+  }
   cJSON *cf = cJSON_AddObjectToObject(o, "confirm");
   if (cf) {
     cJSON_AddBoolToObject(cf, "shell", cfg->confirm_shell);
@@ -1728,6 +1735,7 @@ static int h_settings_x(cst_http_conn_t *c, void *ud) {
   const cJSON *proto = cJSON_GetObjectItem(j, "protocol");
   const cJSON *steps = cJSON_GetObjectItem(j, "max_steps");
   const cJSON *prof = cJSON_GetObjectItem(j, "tool_profile");
+  const cJSON *mode = cJSON_GetObjectItem(j, "mode");
   const cJSON *tools = cJSON_GetObjectItem(j, "tools");
   const cJSON *conf = cJSON_GetObjectItem(j, "confirm");
   cst_protocol_t p = cfg->protocol;
@@ -1742,6 +1750,9 @@ static int h_settings_x(cst_http_conn_t *c, void *ud) {
   else if (prof && (!cJSON_IsString(prof) ||
                     cst_tool_profile_parse(prof->valuestring, &profile) != 0))
     snprintf(bad, sizeof(bad), "未知的工具集（default 或 minimal）");
+  else if (mode && (!cJSON_IsString(mode) ||
+                    !cst_mode_valid(mode->valuestring)))
+    snprintf(bad, sizeof(bad), "工作模式只能是 coding / general");
   else if (tools && !cJSON_IsObject(tools))
     snprintf(bad, sizeof(bad), "tools 要是 {\"名字\": true/false}");
   else if (conf && !cJSON_IsObject(conf))
@@ -1760,6 +1771,11 @@ static int h_settings_x(cst_http_conn_t *c, void *ud) {
   }
   cfg->protocol = p;
   cfg->tool_profile = profile;
+  if (mode) {
+    snprintf(cfg->mode, sizeof(cfg->mode), "%s",
+             cst_mode_name(mode->valuestring));
+    cst_settings_remember_mode(cfg->mode);
+  }
   if (steps)
     cfg->max_steps = (int)steps->valuedouble;
   for (const cJSON *t = tools ? tools->child : NULL; t; t = t->next)

tests/test_attach.c

@@ -325,6 +325,100 @@ static void test_import_file(const char *root) {
          "missing file refused");
 }
 
+/* Documents: text is stored as text, a PDF as its text layer while the mime
+ * still says PDF, and neither is an image as far as the wire is concerned. */
+static void test_documents(const char *root) {
+  char session[1024], src[1024];
+  snprintf(session, sizeof(session), "%.900s/sessions/doc.jsonl", root);
+  char err[256] = "";
+
+  const char *text = "# Notes\n\nFive painters, one canvas.\n";
+  snprintf(src, sizeof(src), "%.900s/notes.md", root);
+  FILE *f = fopen(src, "wb");
+  EXPECT(f != NULL, "write the text file");
+  if (f) {
+    fwrite(text, 1, strlen(text), f);
+    fclose(f);
+  }
+  cst_attachment_t *a = cst_attach_import_file(session, src, err, sizeof(err));
+  EXPECT(a != NULL, "text file imported");
+  if (a) {
+    EXPECT(strcmp(a->mime, "text/plain") == 0, "text mime");
+    EXPECT(!cst_attach_is_image(a) && cst_attach_is_text(a), "not an image");
+    EXPECT(a->pages == 0, "no pages for text");
+    EXPECT(strstr(a->rel, ".txt") != NULL, "text stored as .txt");
+    EXPECT(a->bytes == (long long)strlen(text), "text size");
+    size_t n = 0;
+    char *back = cst_attach_read(session, a, &n, err, sizeof(err));
+    EXPECT(back && n == strlen(text) && memcmp(back, text, n) == 0,
+           "text reads back exactly");
+    free(back);
+    EXPECT(cst_attach_data_url(session, a) == NULL,
+           "a document has no data url");
+    char desc[128];
+    cst_attach_describe(a, desc, sizeof(desc));
+    EXPECT(strstr(desc, "text") != NULL, "describe says text");
+    cst_attach_free(a);
+  }
+
+  /* a one-page PDF with a text layer */
+  static const char PDF[] =
+      "%PDF-1.4\n"
+      "1 0 obj\n<< /Type /Catalog /Pages 2 0 R >>\nendobj\n"
+      "2 0 obj\n<< /Type /Pages /Kids [3 0 R] /Count 1 >>\nendobj\n"
+      "3 0 obj\n<< /Type /Page /Parent 2 0 R /Resources << /Font << /F1 4 0 R "
+      ">> >> /Contents 5 0 R >>\nendobj\n"
+      "4 0 obj\n<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>\n"
+      "endobj\n"
+      "5 0 obj\n<< >>\nstream\n"
+      "BT /F1 12 Tf 72 720 Td (Attached paper abstract) Tj ET\n"
+      "endstream\nendobj\n"
+      "trailer\n<< /Root 1 0 R >>\n%%EOF\n";
+  snprintf(src, sizeof(src), "%.900s/paper.pdf", root);
+  f = fopen(src, "wb");
+  EXPECT(f != NULL, "write the PDF");
+  if (f) {
+    fwrite(PDF, 1, strlen(PDF), f);
+    fclose(f);
+  }
+  err[0] = 0;
+  a = cst_attach_import_file(session, src, err, sizeof(err));
+  EXPECT(a != NULL, "PDF imported");
+  if (a) {
+    EXPECT(strcmp(a->mime, "application/pdf") == 0, "the PDF keeps its mime");
+    EXPECT(a->pages == 1, "page count comes from the extractor");
+    EXPECT(strstr(a->rel, ".txt") != NULL, "the text layer is what is stored");
+    EXPECT(cst_attach_is_text(a), "documents are text on the wire");
+    char desc[128];
+    cst_attach_describe(a, desc, sizeof(desc));
+    EXPECT(strstr(desc, "pdf") != NULL && strstr(desc, "1 page") != NULL,
+           "describe names the PDF and its pages");
+    size_t n = 0;
+    char *back = cst_attach_read(session, a, &n, err, sizeof(err));
+    EXPECT(back && strstr(back, "Attached paper abstract") != NULL,
+           "the extracted text reads back");
+    free(back);
+    cst_attach_free(a);
+  }
+  err[0] = 0;
+  EXPECT(cst_attach_import_file(session, "/nonexistent/x.pdf", err,
+                                sizeof(err)) == NULL,
+         "a missing PDF is refused");
+
+  /* neither image, PDF nor text: a binary blob */
+  static const char binary[] = "\x01\x02\x03\x00\x04\x05";
+  snprintf(src, sizeof(src), "%.900s/blob.bin", root);
+  f = fopen(src, "wb");
+  if (f) {
+    fwrite(binary, 1, sizeof(binary), f);
+    fclose(f);
+  }
+  err[0] = 0;
+  EXPECT(cst_attach_import_file(session, src, err, sizeof(err)) == NULL,
+         "a binary file is refused");
+  EXPECT(strstr(err, "not an image") != NULL, "err says what was expected");
+}
+
 static void test_json_roundtrip(void) {
   cst_attachment_t list[3];
   memset(list, 0, sizeof(list));
@@ -344,6 +438,8 @@ static void test_json_roundtrip(void) {
   list[1].bytes = 4096;
   snprintf(list[1].detail, sizeof(list[1].detail), "high");
   snprintf(list[1].origin, sizeof(list[1].origin), "view_image");
+  snprintf(list[1].mime, sizeof(list[1].mime), "application/pdf");
+  list[1].pages = 12;
 
   snprintf(list[2].id, sizeof(list[2].id), "img-3");
   snprintf(list[2].name, sizeof(list[2].name), "c.webp");
@@ -365,6 +461,9 @@ static void test_json_roundtrip(void) {
     EXPECT(strcmp(back[1].detail, "high") == 0 &&
                strcmp(back[1].origin, "view_image") == 0,
            "detail and origin survive");
+    EXPECT(strcmp(back[1].mime, "application/pdf") == 0 && back[1].pages == 12,
+           "a document keeps its mime and page count");
+    EXPECT(back[2].pages == 0, "pages default to 0");
     EXPECT(strcmp(back[2].mime, "image/webp") == 0 && back[2].width == 0,
            "entry without dimensions");
     EXPECT(strcmp(back[0].detail, "auto") == 0, "missing detail defaults");
@@ -530,6 +629,7 @@ int main(void) {
   test_dib();
   test_store(root);
   test_import_file(root);
+  test_documents(root);
   test_json_roundtrip();
   test_lists();
   test_agent_pending(root);

tests/test_config.c

@@ -106,11 +106,13 @@ static void test_settings(void) {
   snprintf(cfg.provider, sizeof(cfg.provider), "openai");
   snprintf(cfg.model, sizeof(cfg.model), "gpt-5");
   snprintf(cfg.effort, sizeof(cfg.effort), "max");
+  snprintf(cfg.mode, sizeof(cfg.mode), "general");
   CHECK(cst_settings_remember(&cfg) == 0);
 
   CHECK(cst_settings_load(&s) == 0);
   CHECK(strcmp(s.provider, "openai") == 0);
   CHECK(strcmp(s.effort, "max") == 0);
+  CHECK(strcmp(s.mode, "general") == 0);
   CHECK(strcmp(cst_settings_model(&s, "deepseek"), "deepseek-v4-pro") == 0);
   CHECK(strcmp(cst_settings_model(&s, "openai"), "gpt-5") == 0);
   CHECK(s.nmodels == 2);
@@ -145,6 +147,24 @@ static void test_effort(void) {
   free(body);
 }
 
+static void test_mode(void) {
+  CHECK(cst_mode_valid("coding") && cst_mode_valid("general"));
+  CHECK(!cst_mode_valid("code") && !cst_mode_valid(NULL));
+  CHECK(!cst_mode_valid(""));
+  CHECK(strcmp(cst_mode_name("general"), "general") == 0);
+  CHECK(strcmp(cst_mode_name(NULL), CST_DEFAULT_MODE) == 0);
+  CHECK(strcmp(cst_mode_name("nonsense"), "coding") == 0);
+
+  CHECK(cst_settings_remember_mode("general") == 0);
+  cst_settings_t s;
+  CHECK(cst_settings_load(&s) == 0);
+  CHECK(strcmp(s.mode, "general") == 0);
+  /* an unknown value is recorded as the default, not as itself */
+  CHECK(cst_settings_remember_mode("junk") == 0);
+  CHECK(cst_settings_load(&s) == 0);
+  CHECK(strcmp(s.mode, "coding") == 0);
+}
+
 int main(void) {
   CHECK(test_tmpdir(g_dir, sizeof(g_dir), "cst-config") == 0);
   setenv("XDG_CONFIG_HOME", g_dir, 1);
@@ -158,6 +178,7 @@ int main(void) {
   test_creds();
   test_settings();
   test_effort();
+  test_mode();
 
   CHECK(test_rmrf(g_dir) == 0);
   printf("test_config: OK\n");

tests/test_llm_body.c

@@ -406,9 +406,118 @@ static void test_images_on(void) {
   cst_attach_free(img);
 }
 
+/* Every text part of message i, joined (malloc'd, "" when there is none). */
+static char *text_of(const cJSON *root, int i) {
+  const cJSON *m =
+      cJSON_GetArrayItem(cJSON_GetObjectItemCaseSensitive(root, "messages"), i);
+  const cJSON *c = cJSON_GetObjectItemCaseSensitive(m, "content");
+  if (cJSON_IsString(c)) {
+    size_t n = strlen(c->valuestring);
+    char *out = malloc(n + 1);
+    if (out)
+      memcpy(out, c->valuestring, n + 1);
+    return out;
+  }
+  size_t len = 1;
+  const cJSON *p, *t, *s;
+  cJSON_ArrayForEach(p, c) {
+    t = cJSON_GetObjectItemCaseSensitive(p, "type");
+    s = cJSON_GetObjectItemCaseSensitive(p, "text");
+    if (cJSON_IsString(t) && strcmp(t->valuestring, "text") == 0 &&
+        cJSON_IsString(s))
+      len += strlen(s->valuestring) + 1;
+  }
+  char *out = calloc(1, len);
+  if (!out)
+    return NULL;
+  cJSON_ArrayForEach(p, c) {
+    t = cJSON_GetObjectItemCaseSensitive(p, "type");
+    s = cJSON_GetObjectItemCaseSensitive(p, "text");
+    if (cJSON_IsString(t) && strcmp(t->valuestring, "text") == 0 &&
+        cJSON_IsString(s)) {
+      strcat(out, s->valuestring);
+      strcat(out, "\n");
+    }
+  }
+  return out;
+}
+
+/* A document is inlined as text, so a text-only model and a message that
+ * also carries an image both keep it; the image is what becomes a note. */
+static void test_document_parts(void) {
+  char dir[1024], sess[1100], err[256], src[1200];
+  if (test_tmpdir(dir, sizeof(dir), "cst-body-doc") != 0) {
+    EXPECT(0, "scratch dir");
+    return;
+  }
+  snprintf(sess, sizeof(sess), "%s/s.jsonl", dir);
+  snprintf(src, sizeof(src), "%s/paper.pdf", dir);
+  static const char PDF[] =
+      "%PDF-1.4\n"
+      "1 0 obj\n<< /Type /Catalog /Pages 2 0 R >>\nendobj\n"
+      "2 0 obj\n<< /Type /Pages /Kids [3 0 R] /Count 1 >>\nendobj\n"
+      "3 0 obj\n<< /Type /Page /Parent 2 0 R /Resources << /Font << /F1 4 0 R "
+      ">> >> /Contents 5 0 R >>\nendobj\n"
+      "4 0 obj\n<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>\n"
+      "endobj\n"
+      "5 0 obj\n<< >>\nstream\n"
+      "BT /F1 12 Tf 72 720 Td (Inlined paper text) Tj ET\n"
+      "endstream\nendobj\n"
+      "trailer\n<< /Root 1 0 R >>\n%%EOF\n";
+  FILE *f = fopen(src, "wb");
+  EXPECT(f != NULL, "write the PDF");
+  if (!f)
+    return;
+  fwrite(PDF, 1, strlen(PDF), f);
+  fclose(f);
+  cst_attachment_t *doc = cst_attach_import_file(sess, src, err, sizeof(err));
+  EXPECT(doc != NULL, "PDF stored");
+  if (!doc)
+    return;
+  static const unsigned char png[32] = {0x89, 'P', 'N', 'G', '\r', '\n', 0x1A,
+                                        '\n', 0, 0, 0, 13, 'I', 'H', 'D', 'R',
+                                        0, 0, 0, 2, 0, 0, 0, 2};
+  cst_attachment_t *img = cst_attach_import_bytes(
+      sess, "shot.png", (const char *)png, sizeof(png), err, sizeof(err));
+  EXPECT(img != NULL, "image stored");
+  if (!img) {
+    cst_attach_free(doc);
+    return;
+  }
+  cst_attachment_t both[2] = {*doc, *img};
+  cst_message_t m[2];
+  m[0] = msg(CST_ROLE_USER, "what does this say?");
+  m[0].attach = both;
+  m[0].nattach = 2;
+  m[1] = msg(CST_ROLE_USER, "thanks");
+  cst_llm_request_t r;
+  memset(&r, 0, sizeof(r));
+  r.model = "deepseek-flash";
+  r.msgs = m;
+  r.nmsgs = 2;
+  r.images_off = 1; /* a text-only model */
+  r.session_path = sess;
+  cJSON *j = build_req(&r);
+  char *txt = text_of(j, 0);
+  EXPECT(txt && strstr(txt, "[document \"paper.pdf\"") &&
+             strstr(txt, "Inlined paper text") &&
+             strstr(txt, "[-- end of document --]"),
+         "the PDF text is inlined even when images are off");
+  EXPECT(txt && strstr(txt, "[image \"shot.png\"") && strstr(txt, "not sent"),
+         "the image beside it is still only a note");
+  free(txt);
+  char *s = cJSON_PrintUnformatted(j);
+  EXPECT(s && !strstr(s, "image_url"), "no image part with images off");
+  free(s);
+  cJSON_Delete(j);
+  cst_attach_free(doc);
+  cst_attach_free(img);
+}
+
 int main(void) {
   test_images_off();
   test_images_on();
+  test_document_parts();
   test_reasoning_and_prefix();
   test_cache_hints();
   test_tools_snapshot();

tests/test_pdf_text.c

@@ -0,0 +1,250 @@
+/* Text extraction from PDFs: hand-made fixtures for the shapes that matter
+ * (plain content, FlateDecode, CID fonts with ToUnicode CMaps, object
+ * streams) plus the two error paths (encrypted, not a PDF). */
+
+#include "cst_pdf.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+static int failures = 0;
+
+#define CHECK(cond, what)                                                      \
+  do {                                                                         \
+    if (!(cond)) {                                                             \
+      fprintf(stderr, "FAIL %s:%d: %s\n", __FILE__, __LINE__, what);           \
+      failures++;                                                              \
+    }                                                                          \
+  } while (0)
+
+static char *extract(const char *pdf, int *pages, char *err, size_t err_sz) {
+  return cst_pdf_text(pdf, strlen(pdf), pages, err, err_sz);
+}
+
+static int has(const char *hay, const char *needle) {
+  return hay && strstr(hay, needle) != NULL;
+}
+
+/* --- 1. plain, uncompressed content, two lines via Td --------------- */
+
+static const char PLAIN[] =
+    "%PDF-1.4\n"
+    "1 0 obj\n<< /Type /Catalog /Pages 2 0 R >>\nendobj\n"
+    "2 0 obj\n<< /Type /Pages /Kids [3 0 R] /Count 1 >>\nendobj\n"
+    "3 0 obj\n<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] "
+    "/Resources << /Font << /F1 4 0 R >> >> /Contents 5 0 R >>\nendobj\n"
+    "4 0 obj\n<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>\nendobj\n"
+    "5 0 obj\n<< >>\nstream\n"
+    "BT\n/F1 12 Tf\n72 720 Td\n(Line one) Tj\n0 -14 Td\n"
+    "(A \\(paren\\) and a \\\\ backslash) Tj\nET\n"
+    "endstream\nendobj\n"
+    "trailer\n<< /Root 1 0 R >>\n%%EOF\n";
+
+static void test_plain(void) {
+  char err[256] = "";
+  int pages = 0;
+  char *t = extract(PLAIN, &pages, err, sizeof(err));
+  CHECK(t != NULL, err);
+  CHECK(pages == 1, "one page");
+  CHECK(has(t, "Line one"), "first line");
+  CHECK(has(t, "A (paren) and a \\ backslash"), "escapes");
+  CHECK(!has(t, "\r"), "no CR left");
+  free(t);
+}
+
+/* --- 2. FlateDecode content stream ---------------------------------- */
+
+/* raw deflate (zlib, level 9, no header) of
+ * "BT /F1 12 Tf 72 720 Td (Hello, compressed world) Tj ET\n" */
+static const unsigned char FLATE[] = {
+    0x73, 0x0a, 0x51, 0xd0, 0x77, 0x33, 0x54, 0x30, 0x34, 0x52, 0x08, 0x49,
+    0x53, 0x30, 0x37, 0x02, 0x22, 0x03, 0x85, 0x90, 0x14, 0x05, 0x0d, 0x8f,
+    0xd4, 0x9c, 0x9c, 0x7c, 0x1d, 0x85, 0xe4, 0xfc, 0xdc, 0x82, 0xa2, 0xd4,
+    0xe2, 0xe2, 0xd4, 0x14, 0x85, 0xf2, 0xfc, 0xa2, 0x9c, 0x14, 0x4d, 0x85,
+    0x90, 0x2c, 0x05, 0xd7, 0x10, 0x2e, 0x00};
+
+static void test_flate(void) {
+  char pdf[2048];
+  int n = snprintf(pdf, sizeof(pdf),
+                   "%%PDF-1.4\n"
+                   "1 0 obj\n<< /Type /Catalog /Pages 2 0 R >>\nendobj\n"
+                   "2 0 obj\n<< /Type /Pages /Kids [3 0 R] /Count 1 >>\nendobj\n"
+                   "3 0 obj\n<< /Type /Page /Parent 2 0 R /Resources << /Font "
+                   "<< /F1 4 0 R >> >> /Contents 5 0 R >>\nendobj\n"
+                   "4 0 obj\n<< /Type /Font /Subtype /Type1 >>\nendobj\n"
+                   "5 0 obj\n<< /Filter /FlateDecode >>\nstream\n");
+  memcpy(pdf + n, FLATE, sizeof(FLATE));
+  n += (int)sizeof(FLATE);
+  n += snprintf(pdf + n, sizeof(pdf) - (size_t)n,
+                "\nendstream\nendobj\ntrailer\n<< /Root 1 0 R >>\n%%EOF\n");
+  char err[256] = "";
+  int pages = 0;
+  char *t = cst_pdf_text(pdf, (size_t)n, &pages, err, sizeof(err));
+  CHECK(t != NULL, err);
+  CHECK(has(t, "Hello, compressed world"), "inflated text");
+  free(t);
+}
+
+/* 2b. zlib-framed FlateDecode (RFC 1950), which is what real writers emit:
+ * zlib.compress(b"BT /F1 12 Tf 72 720 Td (Zlib framed hello) Tj ET\n"). */
+static const unsigned char ZLIB[] = {
+    0x78, 0xda, 0x73, 0x0a, 0x51, 0xd0, 0x77, 0x33, 0x54, 0x30, 0x34, 0x52,
+    0x08, 0x49, 0x53, 0x30, 0x37, 0x02, 0x22, 0x03, 0x85, 0x90, 0x14, 0x05,
+    0x8d, 0xa8, 0x9c, 0xcc, 0x24, 0x85, 0xb4, 0xa2, 0xc4, 0xdc, 0xd4, 0x14,
+    0x85, 0x8c, 0xd4, 0x9c, 0x9c, 0x7c, 0x4d, 0x85, 0x90, 0x2c, 0x05, 0xd7,
+    0x10, 0x2e, 0x00, 0x33, 0x0f, 0x0d, 0x3a};
+
+static void test_zlib_flate(void) {
+  char pdf[2048];
+  int n = snprintf(pdf, sizeof(pdf),
+                   "%%PDF-1.4\n"
+                   "1 0 obj\n<< /Type /Catalog /Pages 2 0 R >>\nendobj\n"
+                   "2 0 obj\n<< /Type /Pages /Kids [3 0 R] /Count 1 >>\nendobj\n"
+                   "3 0 obj\n<< /Type /Page /Parent 2 0 R /Resources << /Font "
+                   "<< /F1 4 0 R >> >> /Contents 5 0 R >>\nendobj\n"
+                   "4 0 obj\n<< /Type /Font /Subtype /Type1 >>\nendobj\n"
+                   "5 0 obj\n<< /Filter /FlateDecode >>\nstream\n");
+  memcpy(pdf + n, ZLIB, sizeof(ZLIB));
+  n += (int)sizeof(ZLIB);
+  n += snprintf(pdf + n, sizeof(pdf) - (size_t)n,
+                "\nendstream\nendobj\ntrailer\n<< /Root 1 0 R >>\n%%EOF\n");
+  char err[256] = "";
+  int pages = 0;
+  char *t = cst_pdf_text(pdf, (size_t)n, &pages, err, sizeof(err));
+  CHECK(t != NULL, err);
+  CHECK(has(t, "Zlib framed hello"), "zlib header skipped, text inflated");
+  free(t);
+}
+
+/* 2c. an inline image: its bytes are not text and must be skipped. */
+
+static const char INLINE_IMG[] =
+    "%PDF-1.4\n"
+    "1 0 obj\n<< /Type /Catalog /Pages 2 0 R >>\nendobj\n"
+    "2 0 obj\n<< /Type /Pages /Kids [3 0 R] /Count 1 >>\nendobj\n"
+    "3 0 obj\n<< /Type /Page /Parent 2 0 R /Resources << /Font << /F1 4 0 R "
+    ">> >> /Contents 5 0 R >>\nendobj\n"
+    "4 0 obj\n<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>\nendobj\n"
+    "5 0 obj\n<< >>\nstream\n"
+    "BT /F1 12 Tf 72 720 Td (Before the image) Tj ET\n"
+    "q 20 0 0 20 72 700 cm\n"
+    "BI /W 8 /H 8 /CS /RGB /BPC 8 /F /AHx ID\n"
+    "00ff0000ff00ff00ff00ff00 8123<0001> EI Q\n"
+    "BT /F1 12 Tf 72 680 Td (After the image) Tj ET\n"
+    "endstream\nendobj\n"
+    "trailer\n<< /Root 1 0 R >>\n%%EOF\n";
+
+static void test_inline_image(void) {
+  char err[256] = "";
+  int pages = 0;
+  char *t = extract(INLINE_IMG, &pages, err, sizeof(err));
+  CHECK(t != NULL, err);
+  CHECK(has(t, "Before the image"), "text before the inline image");
+  CHECK(has(t, "After the image"), "text after it is still found");
+  CHECK(!has(t, "00ff0000"), "the image bytes were skipped");
+  CHECK(!has(t, "8123"), "its hex data was skipped too");
+  free(t);
+}
+
+/* --- 3. CID font with a ToUnicode CMap ------------------------------ */
+
+static const char CID[] =
+    "%PDF-1.5\n"
+    "1 0 obj\n<< /Type /Catalog /Pages 2 0 R >>\nendobj\n"
+    "2 0 obj\n<< /Type /Pages /Kids [3 0 R] /Count 1 >>\nendobj\n"
+    "3 0 obj\n<< /Type /Page /Parent 2 0 R /Resources << /Font << /F1 4 0 R "
+    ">> >> /Contents 5 0 R >>\nendobj\n"
+    "4 0 obj\n<< /Type /Font /Subtype /Type0 /Encoding /Identity-H "
+    "/ToUnicode 6 0 R >>\nendobj\n"
+    "5 0 obj\n<< >>\nstream\n"
+    "BT /F1 12 Tf 72 720 Td <0001000200030004> Tj ET\n"
+    "endstream\nendobj\n"
+    "6 0 obj\n<< >>\nstream\n"
+    "1 begincodespacerange\n<0000> <FFFF>\nendcodespacerange\n"
+    "2 beginbfchar\n<0001> <4F60>\n<0002> <597D>\nendbfchar\n"
+    "1 beginbfrange\n<0003> <0004> <0041>\nendbfrange\n"
+    "endcmap\nendstream\nendobj\n"
+    "trailer\n<< /Root 1 0 R >>\n%%EOF\n";
+
+static void test_cid(void) {
+  char err[256] = "";
+  int pages = 0;
+  char *t = extract(CID, &pages, err, sizeof(err));
+  CHECK(t != NULL, err);
+  CHECK(has(t, "\xe4\xbd\xa0\xe5\xa5\xbd"), "bfchar maps to 你好");
+  CHECK(has(t, "AB"), "bfrange walks the code points");
+  free(t);
+}
+
+/* --- 4. objects inside an object stream ----------------------------- */
+
+static void test_objstm(void) {
+  char pdf[4096];
+  const char *page = "<< /Type /Page /Parent 2 0 R /Resources << /Font << /F1 "
+                     "4 0 R >> >> /Contents 5 0 R >>";
+  const char *font = "<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>";
+  /* the stream is "num1 off1 num2 off2" -- /N and /First are in the dict --
+   * and offsets count from /First, which is where the bodies start, so
+   * /First is the length of the pairs list itself */
+  char hdr[64];
+  int off4 = (int)strlen(page) + 1; /* object 4 follows the page */
+  int first = snprintf(hdr, sizeof(hdr), "3 0 4 %d ", off4);
+  int n = snprintf(pdf, sizeof(pdf),
+                   "%%PDF-1.5\n"
+                   "1 0 obj\n<< /Type /Catalog /Pages 2 0 R >>\nendobj\n"
+                   "2 0 obj\n<< /Type /Pages /Kids [3 0 R] /Count 1 >>\nendobj\n"
+                   "5 0 obj\n<< >>\nstream\n"
+                   "BT /F1 12 Tf 72 720 Td (Inside an object stream) Tj ET\n"
+                   "endstream\nendobj\n"
+                   "6 0 obj\n<< /Type /ObjStm /N 2 /First %d >>\nstream\n"
+                   "%s%s\n%s",
+                   first, hdr, page, font);
+  n += snprintf(pdf + n, sizeof(pdf) - (size_t)n,
+                "\nendstream\nendobj\n"
+                "trailer\n<< /Root 1 0 R >>\n%%EOF\n");
+  char err[256] = "";
+  int pages = 0;
+  char *t = cst_pdf_text(pdf, (size_t)n, &pages, err, sizeof(err));
+  CHECK(t != NULL, err);
+  CHECK(pages == 1, "one page through the object stream");
+  CHECK(has(t, "Inside an object stream"), "text of the page in the ObjStm");
+  free(t);
+}
+
+/* --- 5. error paths -------------------------------------------------- */
+
+static void test_errors(void) {
+  char err[256] = "";
+  char *t = extract("%PDF-1.7\ntrailer\n<< /Root 1 0 R /Encrypt 9 0 R >>\n",
+                    NULL, err, sizeof(err));
+  CHECK(t == NULL, "encrypted file is refused");
+  CHECK(has(err, "encrypted"), "says it is encrypted");
+
+  err[0] = 0;
+  t = extract("hello, not a pdf at all\n", NULL, err, sizeof(err));
+  CHECK(t == NULL, "non-PDF is refused");
+  CHECK(has(err, "not a PDF"), "says it is not a PDF");
+
+  err[0] = 0;
+  t = extract("%PDF-1.4\n1 0 obj\n<< >>\nendobj\n", NULL, err, sizeof(err));
+  CHECK(t == NULL, "a PDF without text is refused");
+  CHECK(has(err, "no extractable text") || has(err, "no readable pages"),
+        "explains the missing text");
+}
+
+int main(void) {
+  test_plain();
+  test_flate();
+  test_zlib_flate();
+  test_inline_image();
+  test_cid();
+  test_objstm();
+  test_errors();
+  if (failures) {
+    fprintf(stderr, "test_pdf_text: %d failure(s)\n", failures);
+    return 1;
+  }
+  printf("test_pdf_text: OK\n");
+  return 0;
+}

web/app.js

@@ -1717,6 +1717,7 @@ async function showRunSettings() {
   const proto = field('工具协议', select(s.protocols || [], s.protocol));
   const steps = field('每轮步数', Object.assign(el('input'), { type: 'number', min: 1, max: 1000, value: s.max_steps }));
   const prof = field('工具集', select(s.profiles || [], s.tool_profile));
+  const mode = field('工作模式', select(s.modes || [], s.mode));
 
   box.appendChild(el('h4', 'sub', '需要确认（审批模式 ' + (s.approval || '-') + '）'));
   const conf = {};
@@ -1786,6 +1787,7 @@ async function showRunSettings() {
       if (proto.value !== s.protocol) body.protocol = proto.value;
       if (+steps.value !== s.max_steps) body.max_steps = +steps.value;
       if (prof.value !== s.tool_profile) body.tool_profile = prof.value;
+      if (mode.value !== s.mode) body.mode = mode.value;
       const c = {};
       for (const k of Object.keys(conf)) if (conf[k].checked !== !!(s.confirm || {})[k]) c[k] = conf[k].checked;
       if (Object.keys(c).length) body.confirm = c;