- 返回窗收紧:max_bytes(下载,1MB)与 max_chars(返回,默认 12000/硬帽 64000)拆分;单次抓取上下文开销从最坏几十万 token 掉到数千 - offset 续读:超窗尾部提示全文长度与本段区间,转换后全文挂 ctx.run.fetchCache(回合级 LRU 3 条),续读纯本地切片不重抓;字节截断如实标注不完整,不承诺无效续读 - SSRF 防护(默认开):主机名解析结果含回环/私有/链路本地即拒,redirect:manual 逐跳复查至多 5 次;fetch.allow_private: true 可放行;DNS 重绑定为标注的残余风险 - htmlToMarkdown 补剥 nav/header/footer/aside/form 整块与 class/id 样板词启发式丢块,<title> 提成首行;字节截断尾 U+FFFD 去噪 - schema 增 offset/max_chars;旧 config.yml 经 deepMerge 自动获得新默认,无需迁移 - 验证:临时功能脚本 22/22(真 HTTP server 打 executeTool),dep-check 通过;smoke 的 held 超时经 stash 对照确认为既有环境问题,与本改动无关
430 lines
26 KiB
JSON
430 lines
26 KiB
JSON
[
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "db",
|
|
"description": "Execute operations on the session's SQLite database (data.db in the session working directory). The database file is isolated per session and auto-created on first use. For inserting rows (especially batches), prefer op=insert which avoids writing SQL by hand; use exec/query for DDL, updates, deletes and complex SQL.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": [
|
|
"op"
|
|
],
|
|
"properties": {
|
|
"op": {
|
|
"type": "string",
|
|
"enum": [
|
|
"exec",
|
|
"query",
|
|
"insert",
|
|
"tables",
|
|
"schema"
|
|
],
|
|
"description": "Operation type:\n- exec: run a write statement (CREATE / UPDATE / DELETE / ALTER / DROP), in a transaction\n- query: run a read statement (SELECT), returns an array of rows\n- insert: insert one or more rows from row objects (structured, no SQL needed, one transaction)\n- tables: list all tables with row counts\n- schema: show column definitions for a table"
|
|
},
|
|
"sql": {
|
|
"type": "string",
|
|
"description": "A single SQL statement. Required when op is exec or query. Use ? placeholders for parameterized queries to avoid SQL injection; multiple statements are rejected."
|
|
},
|
|
"params": {
|
|
"type": "array",
|
|
"description": "Values bound to the ? placeholders in order. Used by op=exec/query only. Booleans are stored as 0/1.",
|
|
"items": {}
|
|
},
|
|
"table": {
|
|
"type": "string",
|
|
"description": "Table name. Required for insert/schema."
|
|
},
|
|
"rows": {
|
|
"type": "array",
|
|
"description": "Array of row objects for op=insert. Each object maps column names to values; all objects must have the same keys.",
|
|
"items": {
|
|
"type": "object"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "edit_file",
|
|
"description": "This is a tool for applying edits to an existing file.\n\nBefore using this tool, use the `read_file` tool to understand the file's contents and context.\nTo create a new file or overwrite an existing one with completely new contents, use the `write_file` tool instead.\n\nWhen copying text from `read_file` output into `old_text` or `new_text`, strip the line-number prefix and the tab after it, and keep the original indentation exactly.\n\nMatching rules:\n- `old_text` is first matched exactly. If there is no exact match, a fuzzy match tolerating minor whitespace and formatting differences is attempted.\n- If `old_text` matches more than one location (overlapping matches count as separate locations), the edit fails. Include enough surrounding context to make it unique; avoid very short or repetitive `old_text`.\n- If no match is found at all, the edit fails. For very large files the fuzzy stage degrades to per-line whitespace-insensitive exact matching; the error message says so — do not retry the same text, locate with `read_file` by line numbers or use `terminal` with sed.\n\nTo delete whole lines, put the exact line(s) in `old_text` and set `new_text` to an empty string — matched whole lines are removed cleanly together with their line endings (a trailing newline in `old_text` makes no difference).\n\nEdits are applied in order. If one edit fails, the edits before it are already written to disk and the file has changed: the error message tells you how many were applied. You must call `read_file` again before retrying; do not reuse the previous `old_text` values.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": [
|
|
"path",
|
|
"edits"
|
|
],
|
|
"properties": {
|
|
"path": {
|
|
"type": "string",
|
|
"description": "Path of the file to edit, relative to the session working directory. Absolute paths are also accepted."
|
|
},
|
|
"edits": {
|
|
"type": "array",
|
|
"description": "List of edit operations to apply sequentially. Each edit finds `old_text` in the file and replaces it with `new_text`. If any edit fails, the edits before it remain applied.",
|
|
"items": {
|
|
"type": "object",
|
|
"required": [
|
|
"old_text",
|
|
"new_text"
|
|
],
|
|
"properties": {
|
|
"old_text": {
|
|
"type": "string",
|
|
"description": "The text to find in the file. Matched exactly first, then fuzzily (whitespace / minor formatting differences tolerated). Provide enough context to make the match unique; short or repeated snippets are reported as ambiguous. A trailing newline, if present, is stripped before matching. For whole-line deletion, put the exact line(s) in old_text and pass an empty new_text."
|
|
},
|
|
"new_text": {
|
|
"type": "string",
|
|
"description": "The replacement text. Use an empty string together with a trailing-newline-free `old_text` to delete a whole line."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "fetch",
|
|
"description": "Fetches a URL and returns its content as Markdown. Only http and https are supported; if the scheme is omitted, https is assumed.\n\nHTML pages are converted to Markdown. JSON, XML, plain text, and Markdown responses are returned as-is. Binary responses are not returned — only their HTTP status, content-type, and size.\n\nThe response always starts with a line `HTTP <status>`, followed by the body. Check the status line: a non-2xx status means the fetch did not succeed, even if body content is present.\n\nReturned text is capped per call (default is modest; raise one call with `max_chars` up to a hard cap). When truncated, the tail hint gives the total length and the `offset` to continue from — re-call with that `offset` to page through WITHOUT re-downloading. Most pages fit in the first window; only page further when you actually need more.\n\nTargets that resolve to private/loopback addresses are refused (SSRF guard). Redirects are followed up to 5 hops, each hop checked.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": [
|
|
"url"
|
|
],
|
|
"properties": {
|
|
"url": {
|
|
"type": "string",
|
|
"description": "The URL to fetch. Must be http or https; if no scheme is given, https is assumed."
|
|
},
|
|
"offset": {
|
|
"type": "integer",
|
|
"minimum": 0,
|
|
"default": 0,
|
|
"description": "Character offset into the converted page body, for continuing a truncated fetch. Use the offset value given in the previous truncation hint. Requires no re-download."
|
|
},
|
|
"max_chars": {
|
|
"type": "integer",
|
|
"minimum": 1,
|
|
"description": "Max characters to return for this call. Optional; raise only when the default window clearly cut off content you need. Values above the hard cap are clamped."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "handoff",
|
|
"description": "Hand off from the advising phase to the execution phase. Call this when the task brief is ready. The system stores your `brief` as the task brief and switches to execution. There are three cases:\n\n- ready: The requirement is clear enough to execute.\n- user_skip: The user explicitly asks to stop planning with you (\"just move on\", or similar) — this skips only the advising conversation, it never waives the user's later confirmations. Do not call this on tone or mood alone — only on explicit signals.\n- user_stuck: You have asked 2-3 rounds and the user is still not providing key information, and they seem to want to move on.\n\nWhen reason is not \"ready\", the `brief` must carry the user's own words plus every open question under a Missing section — the executor is required to ask the user these before acting. Do not invent a methodology or generic plan.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": [
|
|
"reason",
|
|
"brief",
|
|
"title"
|
|
],
|
|
"properties": {
|
|
"reason": {
|
|
"type": "string",
|
|
"enum": [
|
|
"ready",
|
|
"user_skip",
|
|
"user_stuck"
|
|
],
|
|
"description": "Why the handoff is happening."
|
|
},
|
|
"brief": {
|
|
"type": "string",
|
|
"description": "The task brief content, in Markdown. Follow the structure described in your system prompt."
|
|
},
|
|
"title": {
|
|
"type": "string",
|
|
"description": "A concise title for this conversation, in the user's language (3-7 words, or 6-14 Chinese characters). Straight to the title: no quotes, no prefix like \"Title:\"."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "lab",
|
|
"description": "Unified entry point for calling any available tool by name.\n\nCall a tool:\n lab(tool: \"<name>\", args: {<arguments>})\n\nThe target tool's arguments go inside `args` as a JSON object. Omit `args` for tools that take no arguments.\n\nDiscovering tools:\n lab(tool: \"help\") → list all tools with a one-line description each\n lab(tool: \"help\", args: {tool: \"<name>\"}) → full description and parameter schema of <name>\n\nAn unknown tool name also returns the list of available tools.\nNested lab calls are rejected; inner tool errors surface unchanged.\n\nCalling a tool directly and calling it through lab are equivalent. When the tool you need is already in your tool list, call it directly. Use lab to discover or reach tools that are not in the current list.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": [
|
|
"tool"
|
|
],
|
|
"properties": {
|
|
"tool": {
|
|
"type": "string",
|
|
"description": "Name of the tool to call, or \"help\"."
|
|
},
|
|
"args": {
|
|
"type": "object",
|
|
"description": "Arguments for the target tool, matching its own schema (look it up with lab(tool: \"help\", args: {tool: \"<name>\"}) if unsure). Omit for tools that take no arguments."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "mint_public_link",
|
|
"description": "Create a short-lived, publicly reachable URL for a local file, so an external service that cannot authenticate can download it.\nUse this when another tool or API needs to fetch a local file by URL. Returns the URL as plain text on a single line.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": [
|
|
"path"
|
|
],
|
|
"properties": {
|
|
"path": {
|
|
"type": "string",
|
|
"description": "Path of the file to publish, relative to the session working directory. Absolute paths inside the session working directory are also accepted."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "profile",
|
|
"description": "Maintain the current user's profile — stable facts that persist across conversations and get injected into the context of NEW sessions (the current session's injected copy is frozen). Ops: list (read the live profile), set (honorific or industry, single short value), add (append preference tags), remove (delete exact preference tags). Rules: only record what the user has clearly stated or asked to be remembered (form of address, domain, stable output/work preferences); never guess personality, never store one-time task parameters; brief tags beat essays. Preference is a 、-separated tag list (each tag ≤15 chars, ≤24 tags, ≤300 chars total; overflow is rejected — consolidate or remove first). When unsure what is already recorded, op=list returns live state — trust it over memory.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": ["op"],
|
|
"properties": {
|
|
"op": { "type": "string", "enum": ["list", "set", "add", "remove"], "description": "list = read live profile; set = single-value honorific/industry; add/remove = preference tags." },
|
|
"honorific": { "type": "string", "description": "op=set: how to address the user (≤20 chars, e.g. 王工). Pass empty string to clear. Exactly one of honorific/industry per call." },
|
|
"industry": { "type": "string", "description": "op=set: the user's industry/domain (≤20 chars, e.g. 金融). Pass empty string to clear." },
|
|
"tags": { "type": "array", "items": { "type": "string" }, "description": "op=add/remove: preference tag list, e.g. [\"偏好简洁回复\", \"图表中文标注\"]. Matching is exact text." }
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "read_file",
|
|
"description": "Reads the content of a file.\n\nText files: each returned line is prefixed with a line number right-aligned in a 6-character field, followed by a tab, then the line content.\n\nLarge text files (roughly over 16 KB) are not returned in full: you get an outline listing top-level symbols (or Markdown headings) with line numbers instead. The outline IS a successful response — do NOT retry the same call without a line range; use the outline line numbers with `start_line` / `end_line` to read specific sections. If no outline can be extracted, a first-1KB excerpt is returned instead. Supplying `start_line` or `end_line` disables outline mode.\n\nImage files (PNG, JPEG, WebP, GIF, BMP, TIFF) are returned as visual content you can analyze directly, but only if the current model supports vision; otherwise a text placeholder is returned — that placeholder is not an error. The tool result itself carries a text notice only; the actual image pixels arrive in a separate user message right after the batch of tool results: that message lists per-image labels matching each image to its read_file receipt, then the image blocks in receipt order, and asks you to briefly describe each image before continuing. Never re-read an image already delivered in the current turn; if pixels never arrive, tell the user instead of retrying. Very large images (roughly over 50 MB) are skipped, and images may be downscaled (long edge ~2000 px, re-encoded as JPEG) before being returned.\n\nBinary files are not returned as text; a short notice is returned instead. Text files over 32 MB cannot be read by this tool — use `terminal` (grep -n / head / sed -n).",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": [
|
|
"path"
|
|
],
|
|
"properties": {
|
|
"path": {
|
|
"type": "string",
|
|
"description": "Path of the file to read, relative to the session working directory. Absolute paths are also accepted."
|
|
},
|
|
"start_line": {
|
|
"type": "integer",
|
|
"nullable": true,
|
|
"description": "Optional 1-based line number to start reading from.",
|
|
"default": null,
|
|
"minimum": 1
|
|
},
|
|
"end_line": {
|
|
"type": "integer",
|
|
"nullable": true,
|
|
"description": "Optional 1-based line number to end reading at (inclusive). Must be >= start_line. Supplying either bound disables outline mode.",
|
|
"default": null,
|
|
"minimum": 1
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "recall",
|
|
"description": "Access your long-term memory: the work diary. Each finished session leaves one short fragment (a few dozen characters, headed by the source session id), stored permanently; only the newest fragments were injected at session start. When the user vaguely recalls something from the past, search is your primary entry — you cannot know what you have forgotten. Read-only.\n\nop=search Requires query (keywords; space-separated words rank better, e.g. '身份证 水印'). Fuzzy fragment-level match across ALL dates (Chinese tolerant to partial phrases), best matches first. Optional count (default 10, max 30).\nop=days No arguments. Index of diary days (date + fragment count) — use when the user remembers roughly WHEN but not what; then op=day.\nop=day Requires date (YYYY-MM-DD, as listed by op=days). Full fragments of that day.\nop=files Requires id (the session id from a diary fragment's 【…】 heading). Files of that past session that still exist on disk right now.\nop=link Requires id and path (a name from op=files). Mint a temporary download link.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": [
|
|
"op"
|
|
],
|
|
"properties": {
|
|
"op": {
|
|
"type": "string",
|
|
"enum": [
|
|
"search",
|
|
"days",
|
|
"day",
|
|
"files",
|
|
"link"
|
|
],
|
|
"description": "What to recall: search = keyword fuzzy over all diary fragments (primary); days = which dates have entries; day = one date's full diary; files = a past session's current artifacts; link = a download link for one of them."
|
|
},
|
|
"query": {
|
|
"type": "string",
|
|
"description": "op=search: keywords to look for (space-separated words rank best, e.g. '身份证 水印'). Chinese and English both supported, case-insensitive."
|
|
},
|
|
"count": {
|
|
"type": "integer",
|
|
"description": "op=search: max fragments to return (default 10, max 30)."
|
|
},
|
|
"date": {
|
|
"type": "string",
|
|
"description": "op=day: the day to open, YYYY-MM-DD exactly as shown by op=days."
|
|
},
|
|
"id": {
|
|
"type": "string",
|
|
"description": "op=files / op=link: the source session id as written inside a diary fragment's 【…】 heading (e.g. 'task-20260929-003')."
|
|
},
|
|
"path": {
|
|
"type": "string",
|
|
"description": "op=link: file name inside that session's task directory, exactly as listed by op=files."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "schedule",
|
|
"description": "Manage the recurring scheduled task bound to the CURRENT session. At most one task per session; it is deleted together with the session. At each trigger, the prompt is sent to this session as a new user message. Schedule times are interpreted in Asia/Shanghai (UTC+8). Call this ONLY when the user explicitly asks for something to run periodically or at a specific time.\n\nop=get No arguments.\nop=list_all No arguments. Lists every scheduled task of the current user across all sessions (update/delete still act on the CURRENT session only; other rows name their session id so the user can switch there).\nop=create Requires cron_expr, prompt and brief.\nop=update Requires at least one of cron_expr, prompt; only the given fields change.\nop=delete No arguments.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": [
|
|
"op"
|
|
],
|
|
"properties": {
|
|
"op": {
|
|
"type": "string",
|
|
"enum": [
|
|
"get",
|
|
"create",
|
|
"update",
|
|
"delete",
|
|
"list_all"
|
|
],
|
|
"description": "Operation to perform on the current session's scheduled task."
|
|
},
|
|
"cron_expr": {
|
|
"type": "string",
|
|
"description": "Standard 5-field cron expression in Asia/Shanghai (UTC+8), e.g. '0 9 * * *' for 09:00 Beijing time every day. The interval between two consecutive runs must be at least 1 hour. Required with op=create; optional with op=update (next run time is recomputed)."
|
|
},
|
|
"prompt": {
|
|
"type": "string",
|
|
"description": "The message to send to this session at each trigger. Write it as a self-contained instruction: previous conversation history is archived before each run, so this prompt is the only input the model will see. The output stays in this session for the user to view; if it must reach the user proactively, state how in the prompt (e.g. via a skill or webhook). Required with op=create; optional with op=update."
|
|
},
|
|
"brief": {
|
|
"type": "string",
|
|
"description": "One short plain-language line (<= 40 chars) saying what this task actually accomplishes, e.g. 'collect and produce a daily news PDF report'. It is written into the assistant's long-term memory diary so the recurring job can be recalled later. Required with op=create."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "skill",
|
|
"description": "Use the skills installed on this server. A skill is a directory under the skill root whose SKILL.md defines its purpose and input_schema.\n\nop=list No arguments.\nop=get Requires name.\nop=run Requires name; input_args optional (default {}).\n\nop=list: lists all installed skills with a one-line description each, read live from the skill root; use it to choose among skills or to confirm what is installed. An empty skill set returns an empty list — that is not an error.\nop=get: returns the full raw SKILL.md (front matter included): purpose, input_schema, and usage notes. Call it before op=run with a skill you have not used in this conversation. A nonexistent skill returns an error.\nop=run: executes the skill with input_args validated against its input_schema (a validation error names the missing fields). The entry script receives a JSON string as its only CLI argument, so input_args must be a JSON object.\n- Returns the skill's combined stdout+stderr as plain text after it exits; exit 0 with no output yields '(无输出)'. A non-zero exit raises an error containing the output and [exit code: N].\n- Direct output files via arguments: relative paths in arguments are resolved against the session working directory; do not rely on the skill's cwd.\n- Default timeout 120 seconds: the process group is killed and the error includes partial output collected so far (a timeout is not a skill failure).",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": [
|
|
"op"
|
|
],
|
|
"properties": {
|
|
"op": {
|
|
"type": "string",
|
|
"enum": [
|
|
"list",
|
|
"get",
|
|
"run"
|
|
],
|
|
"description": "Operation to perform on skills."
|
|
},
|
|
"name": {
|
|
"type": "string",
|
|
"description": "Name of the skill (subdirectory name under the skill root directory). Required with op=get and op=run."
|
|
},
|
|
"input_args": {
|
|
"type": "object",
|
|
"description": "Dictionary of input arguments for the skill. Keys and values should match the skill's input_schema (call op=get first if unsure). Example: {\"input\": \"file.md\", \"output\": \"out.pdf\"}. Used only with op=run; omit it for skills that take no arguments."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "terminal",
|
|
"description": "Executes a shell one-liner and returns combined stdout/stderr output.\n\n- Run commands relative to the session working directory. Use the `cd` parameter to specify a different directory if needed.\n- Do not use shell substitutions or interpolations (e.g., `$VAR`, `${VAR}`, `$(...)`, backticks). Resolve values yourself first.\n- Do not pipe output to `head` or `tail`; use the `head_lines` and `tail_lines` parameters to limit what is returned while keeping full output visible to the user.\n- Avoid commands that run indefinitely (servers, watchers). For long-running commands, set `timeout_ms`.\n- Each invocation starts a new shell; do not rely on state from previous calls.\n- If a command may open a pager or editor, disable it using environment variables (e.g., `GIT_PAGER=cat`, `EDITOR=true`).",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": [
|
|
"command"
|
|
],
|
|
"properties": {
|
|
"command": {
|
|
"type": "string",
|
|
"description": "The shell one-liner to execute. Do not include shell substitutions; use literal values."
|
|
},
|
|
"cd": {
|
|
"type": "string",
|
|
"nullable": true,
|
|
"description": "Optional working directory for the command. If omitted, runs in the session working directory. Accepts relative or absolute path."
|
|
},
|
|
"timeout_ms": {
|
|
"type": "integer",
|
|
"nullable": true,
|
|
"description": "Optional maximum runtime in milliseconds. If exceeded, the process is killed.",
|
|
"minimum": 0
|
|
},
|
|
"head_lines": {
|
|
"type": "integer",
|
|
"nullable": true,
|
|
"description": "Return only the first N lines of output to the model. The user still sees full live output.",
|
|
"minimum": 0,
|
|
"default": null
|
|
},
|
|
"tail_lines": {
|
|
"type": "integer",
|
|
"nullable": true,
|
|
"description": "Return only the last N lines of output to the model. The user still sees full live output.",
|
|
"minimum": 0,
|
|
"default": null
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "write_file",
|
|
"description": "Creates a new file or overwrites an existing file with the given content.\n\nParent directories are created automatically, so the path does not need to exist beforehand.\n\nOverwriting replaces the file's entire content irreversibly. If the file already exists, read it first, or use `edit_file` for targeted changes instead.\n\nText is written as UTF-8. To produce binary files, use `terminal` instead.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"required": [
|
|
"path",
|
|
"content"
|
|
],
|
|
"properties": {
|
|
"path": {
|
|
"type": "string",
|
|
"description": "Path of the file to create or overwrite, relative to the session working directory. Absolute paths inside the working directory are also accepted."
|
|
},
|
|
"content": {
|
|
"type": "string",
|
|
"description": "The entire content to write. Required — pass an empty string to create an empty file; omitting it is an error."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
]
|