feat(sheets): add +formula-verify shortcut for verify_formula tool

internal/cmdutil/secheader.go

@@ -78,6 +78,14 @@
 	if v := AgentTraceValue(); v != "" {
 		h.Set(HeaderAgentTrace, v)
 	}
+	// PPE 路由 header（开发自测）：仅当对应 env var 非空时注入，避免污染生产构建。
+	// 二者独立——通常配对使用：LARKSUITE_CLI_TT_ENV=<ppe-env> + LARKSUITE_CLI_USE_PPE=1。
+	if v := strings.TrimSpace(os.Getenv(envvars.CliTtEnv)); v != "" {
+		h.Set("x-tt-env", v)
+	}
+	if v := strings.TrimSpace(os.Getenv(envvars.CliUsePpe)); v != "" {
+		h.Set("x-use-ppe", v)
+	}
 	return h
 }
 

internal/envvars/envvars.go

@@ -21,6 +21,12 @@ const (
 
 	CliAgentTrace = "LARKSUITE_CLI_AGENT_TRACE"
 
+	// PPE / 灰度环境路由（开发自测用）：若设置，会注入对应 HTTP header 把请求
+	// 稳定地打到指定 PPE/灰度集群。生产构建禁止设置；通过 env 而非硬编码，
+	// 是为了让 sync-global.sh 在打包前 export 一次就能稳定生效，commit 不污染线上。
+	CliTtEnv  = "LARKSUITE_CLI_TT_ENV"  // → x-tt-env header value
+	CliUsePpe = "LARKSUITE_CLI_USE_PPE" // → x-use-ppe header value (typically "1")
+
 	CliProxyEnable  = "LARKSUITE_CLI_PROXY_ENABLE"
 	CliProxyAddress = "LARKSUITE_CLI_PROXY_ADDRESS"
 	CliCAPath       = "LARKSUITE_CLI_CA_PATH"

shortcuts/sheets/data/flag-defs.json

@@ -1,4 +1,67 @@
 {
+  "+formula-verify": {
+    "risk": "read",
+    "flags": [
+      {
+        "name": "url",
+        "kind": "public",
+        "type": "string",
+        "required": "xor",
+        "desc": "Spreadsheet URL (XOR with `--spreadsheet-token`)"
+      },
+      {
+        "name": "spreadsheet-token",
+        "kind": "public",
+        "type": "string",
+        "required": "xor",
+        "desc": "Spreadsheet token (XOR with `--url`)"
+      },
+      {
+        "name": "sheet-id",
+        "kind": "public",
+        "type": "string_slice",
+        "required": "optional",
+        "desc": "Sheet reference_id(s); repeat or comma-separate to scan multiple sheets. Omit to scan all visible sheets."
+      },
+      {
+        "name": "sheet-name",
+        "kind": "public",
+        "type": "string_slice",
+        "required": "optional",
+        "desc": "Sheet name(s); repeat or comma-separate to scan multiple sheets. Omit to scan all visible sheets."
+      },
+      {
+        "name": "range",
+        "kind": "own",
+        "type": "string_slice",
+        "required": "optional",
+        "desc": "Optional A1 ranges (e.g. `A1:Z200`); repeat or comma-separate for multiple ranges. Omit to scan each sheet's current_region."
+      },
+      {
+        "name": "max-locations",
+        "kind": "own",
+        "type": "int",
+        "required": "optional",
+        "desc": "Max locations / samples per error type; default 20.",
+        "default": "20"
+      },
+      {
+        "name": "cell-limit",
+        "kind": "own",
+        "type": "int",
+        "required": "optional",
+        "desc": "Total cell scan cap (default 50000). When exceeded, `has_more=true` and caller should narrow `--range` to continue.",
+        "default": "50000"
+      },
+      {
+        "name": "exit-on-error",
+        "kind": "own",
+        "type": "bool",
+        "required": "optional",
+        "desc": "When status=errors_found, exit non-zero. Useful for CI / xlsx-style write-then-verify pipelines."
+      }
+    ]
+  },
   "+workbook-info": {
     "risk": "read",
     "flags": [
@@ -526,7 +589,7 @@
         "kind": "own",
         "type": "string",
         "required": "optional",
-        "desc": "Typed table payload as JSON (same shape as `+table-put`): top-level `{\"sheets\":[...]}`, with each array item a sub-sheet `{name, start_cell?, mode?, header?, allow_overwrite?, columns:[\"colA\",\"colB\",...], data:[[...]], dtypes?:{colA:pandasDtype, ...}, formats?:{colA:numberFormat, ...}}` — `name` and the outer `sheets` envelope are both required. Agents typically use `df_to_sheet(df, name)` from `scripts/sheets_df.py` to pack each DataFrame into one item, then wrap the list in `{\"sheets\":[...]}`. Mutually exclusive with --values. Creates the workbook, then writes typed type-faithful data (dates land as real dates, numbers keep precision).",
+        "desc": "Typed table payload as JSON (same shape as `+table-put`): a top-level `sheets` array, each item `{name, start_cell?, mode?, header?, allow_overwrite?, columns:[\"colA\",\"colB\",...], data:[[...]], dtypes?:{colA:pandasDtype, ...}, formats?:{colA:numberFormat, ...}}`. Agents typically build it from a DataFrame via `{**json.loads(df.to_json(orient=\"split\")), \"dtypes\": df.dtypes.astype(str).to_dict()}`. Mutually exclusive with --values and --dataframe. Creates the workbook, then writes typed type-faithful data (dates land as real dates, numbers keep precision).",
         "input": [
           "file",
           "stdin"
@@ -543,6 +606,13 @@
           "stdin"
         ]
       },
+      {
+        "name": "dataframe",
+        "kind": "own",
+        "type": "string",
+        "required": "optional",
+        "desc": "Single-sheet typed table from one Arrow IPC file (Feather v2 — what `pandas.DataFrame.to_feather()` writes), mutually exclusive with --values and --sheets. Pass `@<path>` for a file or `-` for binary stdin (same convention as other input flags). Arrow bytes are read raw — no TrimSpace / BOM strip — so the IPC magic survives intact (unlike text input flags). Column types come from the Arrow schema; per-column `number_format` may be set via Arrow field metadata. Creates the workbook and fills its default sheet (`Sheet1` — adopted in place, no empty Sheet1 left behind). For multi-sheet or non-default placement, use `--sheets` instead."
+      },
       {
         "name": "dry-run",
         "kind": "system",
@@ -593,7 +663,7 @@
         "kind": "own",
         "type": "string",
         "required": "optional",
-        "desc": "Local save path. When omitted, **only the export task is triggered + polled, the file is NOT downloaded** (returns file_token / status so a later step can resume the download). Pass a concrete path (e.g. `./out.xlsx`) or a directory (`.` keeps the server-provided filename) to download. Note: the equivalent `lark-cli drive +export --doc-type sheet` uses three separate flags (`--output-dir` / `--file-name` / `--overwrite`) and defaults to downloading into the current directory; this wrapper collapses them into a single `--output-path` for ergonomics but defaults to no-download — fall back to `drive +export` if the split flag set fits better."
+        "desc": "Local save path; export is triggered but not downloaded when omitted"
       },
       {
         "name": "dry-run",
@@ -1380,6 +1450,13 @@
         "required": "optional",
         "desc": "Treat the first row as data instead of a header (columns get positional names col1, col2, ...)"
       },
+      {
+        "name": "dataframe-out",
+        "kind": "own",
+        "type": "string",
+        "required": "optional",
+        "desc": "Write the typed table as one Arrow IPC file (Feather v2) instead of the default JSON. Pass `@<path>` for a file or `-` for binary stdout (same convention as other binary I/O flags). Mirror of the input-side `--dataframe` on `+table-put` / `+workbook-create` — pandas users round-trip via `df = pd.read_feather(\"x.arrow\")` or `pd.read_feather(io.BytesIO(stdout))`. Single-sheet only: requires `--sheet-id` or `--sheet-name`; whole-workbook reads keep the default JSON path. Column types come from the typed read-back (string/number/date/bool); per-column `number_format` is preserved as Arrow field metadata so the Arrow file can round-trip straight back through `+table-put --dataframe`."
+      },
       {
         "name": "dry-run",
         "kind": "system",
@@ -2062,19 +2139,26 @@
         "name": "sheets",
         "kind": "own",
         "type": "string",
-        "required": "required",
-        "desc": "Typed table payload (pandas-DataFrame-shaped) as JSON: top-level `{\"sheets\":[...]}`, with each array item a sub-sheet `{name, start_cell?, mode?, header?, allow_overwrite?, columns:[\"colA\",\"colB\",...], data:[[...]], dtypes?:{colA:pandasDtype, ...}, formats?:{colA:numberFormat, ...}}` — `name` and the outer `sheets` envelope are both required. Agents typically use `df_to_sheet(df, name)` from `scripts/sheets_df.py` to pack each DataFrame into one item, then wrap the list in `{\"sheets\":[...]}`. `dtypes` values are pandas dtype strings (`int64`, `float64`, `Int64`, `bool`, `boolean`, `datetime64[ns]`, `object`, ...); the writer maps them to internal string/number/date/bool — omit `dtypes` and a column writes as text (good for raw CSV-shaped data). `formats[col]` is an Excel number_format string (e.g. `#,##0.00`, `0.0%`, `yyyy-mm`); when absent, date columns default to `yyyy-mm-dd` and string columns to text format (`@`).",
+        "required": "xor",
+        "desc": "Typed table payload (pandas-DataFrame-shaped) as JSON, XOR with `--dataframe`: a top-level `sheets` array, each item `{name, start_cell?, mode?, header?, allow_overwrite?, columns:[\"colA\",\"colB\",...], data:[[...]], dtypes?:{colA:pandasDtype, ...}, formats?:{colA:numberFormat, ...}}`. Agents typically build it with `{**json.loads(df.to_json(orient=\"split\")), \"dtypes\": df.dtypes.astype(str).to_dict()}`. `dtypes` values are pandas dtype strings (`int64`, `float64`, `Int64`, `bool`, `boolean`, `datetime64[ns]`, `object`, ...); the writer maps them to internal string/number/date/bool — omit `dtypes` and a column writes as text (good for raw CSV-shaped data). `formats[col]` is an Excel number_format string (e.g. `#,##0.00`, `0.0%`, `yyyy-mm`); when absent, date columns default to `yyyy-mm-dd` and string columns to text format (`@`).",
         "input": [
           "file",
           "stdin"
         ]
       },
+      {
+        "name": "dataframe",
+        "kind": "own",
+        "type": "string",
+        "required": "xor",
+        "desc": "Single-sheet typed table from one Arrow IPC file (a.k.a. Feather v2 — what `pandas.DataFrame.to_feather()` writes), XOR with `--sheets`. Pass `@<path>` for a file or `-` for binary stdin (same convention as other input flags). Arrow bytes are read raw — no TrimSpace / BOM strip — so the IPC magic survives intact (unlike text input flags). Column types come from the Arrow schema (int*/uint*/float* → number, date32/date64/timestamp → date, utf8/large_utf8 → string, bool → bool); per-column `number_format` may be set via Arrow field metadata (`pa.field(\"price\", pa.float64(), metadata={b\"number_format\": b\"$#,##0.00\"})`). Writes the sheet at default placement: name `Sheet1` (created when absent), overwrite from A1 with header. For a different sheet name, anchor, mode, or to write multiple sheets, use `--sheets` instead."
+      },
       {
         "name": "styles",
         "kind": "own",
         "type": "string",
         "required": "optional",
-        "desc": "Visual operations applied after the typed write, as JSON: top-level `{styles:[...]}`. Each item corresponds to one written sheet and must include `name`, plus at least one of `cell_styles` / `row_sizes` / `col_sizes` / `cell_merges`. `cell_styles` entries use +cells-set-style fields with a cell range; row/col sizes use dimension ranges plus type/size; merges use cell ranges plus optional merge_type. The styles array length/order/name must match the written sheets in --sheets.sheets. Run `+table-put --print-schema --flag-name styles` for the full cell_styles field schema.",
+        "desc": "Visual operations applied after the typed write, as JSON: top-level `{styles:[...]}`. Each item corresponds to one written sheet and must include `name`, plus at least one of `cell_styles` / `row_sizes` / `col_sizes` / `cell_merges`. `cell_styles` entries use +cells-set-style fields with a cell range; row/col sizes use dimension ranges plus type/size; merges use cell ranges plus optional merge_type. The styles array length/order/name must match the written sheets: with --sheets, match --sheets.sheets; with --dataframe (single sheet named Sheet1), pass exactly one styles item with name `Sheet1`. Run `+table-put --print-schema --flag-name styles` for the full cell_styles field schema.",
         "input": [
           "file",
           "stdin"
@@ -4747,5 +4831,39 @@
         "desc": ""
       }
     ]
+  },
+  "+changeset-get": {
+    "risk": "read",
+    "flags": [
+      {
+        "name": "url",
+        "kind": "public",
+        "type": "string",
+        "required": "xor",
+        "desc": "Spreadsheet URL (XOR with `--spreadsheet-token`)"
+      },
+      {
+        "name": "spreadsheet-token",
+        "kind": "public",
+        "type": "string",
+        "required": "xor",
+        "desc": "Spreadsheet token (XOR with `--url`)"
+      },
+      {
+        "name": "start-revision",
+        "kind": "own",
+        "type": "int",
+        "required": "required",
+        "desc": "Start version (CS revision); the before baseline for review (must be >= 1)"
+      },
+      {
+        "name": "end-revision",
+        "kind": "own",
+        "type": "int",
+        "required": "optional",
+        "desc": "End version (CS revision); defaults to the latest revision. Gap (end-start+1) must be <= 20",
+        "default": "-1"
+      }
+    ]
   }
 }