/sap-se16n

name: sap-se16n
description: |
  Queries any SAP table via SE16N using SAP GUI Scripting and downloads the
  result set as a tab-delimited text file. Supports filtering by any combination
  of table fields with single value, multi-value (IN list), or range (BT)
  selection, and any of the standard SE16N operators (EQ, NE, GT, LT, GE, LE,
  BT, NB, CP, NP, IN). Optionally restricts the output columns to a specific
  set of fields; if no SELECT list is given, all fields are returned. Detects
  the "no values found" path and writes a marker file instead of an empty
  download. Typical use: dump rows from any SAP table for inspection or as
  reference data for development. Snapshot modes add a table-state assertion
  primitive: `snapshot save <name>` captures a query result under
  {artifact_dir}\snapshots; `snapshot diff <a> <b>` row-diffs two snapshots on
  declared key columns (ignoring volatile columns) via the shared keyed-diff
  engine — ADDED/REMOVED/CHANGED/SAME; `snapshot list` enumerates them.
  Prerequisites: Active SAP GUI session (use /sap-login first). `snapshot diff` /
  `snapshot list` are pure-local and need no SAP session.
argument-hint: "<TABLE> [field=value ...] [select=F1,F2,...]  |  snapshot save <name> <TABLE> [filters] --keys=K1,K2 [--ignore=V1,V2]  |  snapshot diff <a> <b> [--keys=..] [--ignore=..]  |  snapshot list"

SAP SE16N Table Query Skill

You query a SAP table via transaction SE16N and download the result set as a tab-delimited text file. Filters and the optional output-field list are passed to the underlying VBScript via a side-channel parameters file so that an arbitrary number of filter fields and values can be specified.

Task: $ARGUMENTS

**Mode dispatch.** If the first token is `snapshot`, go to **Snapshot Modes** (below): `save` runs the normal query flow (Steps 0–6) then captures the result; `diff` / `list` are pure-local and skip the SAP query. If the first token is `agg`, go to **Aggregation Mode (SE16H)** — server-side GROUP BY + MIN/MAX/AVG + per-group count, a separate SAP flow (transaction SE16H) that does NOT run Steps 3–6. Any other first token is the **normal query flow** (Steps 0–6, default — unchanged).

---

Shared Resources

| File | Purpose | |---|---| | `<SAP_DEV_CORE_SHARED_DIR>/rules/skill_operating_rules.md` | Mandatory operating rules | | `<SAP_DEV_CORE_SHARED_DIR>/rules/language_independence_rules.md` | GUI-scripting language independence — identify by component ID + DDIC field name, status-bar checks via `MessageType` codes (S/W/E/I/A), VKey instead of menu-text, no branching on `.Text`/`.Tooltip`/window titles | | `<SKILL_DIR>/references/sap_se16n_snapshot.ps1` | Snapshot `save`/`diff`/`list` (pure-local); the diff delegates to the shared keyed-diff engine. | | `<SKILL_DIR>/references/sap_se16h_agg.vbs` | `agg` mode — drives SE16H (program `SAPLSE16N`, advanced screen) for server-side GROUP BY + MIN/MAX/AVG; reads the grouped ALV via the GridView API (no export dialog). Tokens: `%%TABLE_NAME%%`, `%%PARAMS_FILE%%`, `%%OUTPUT_FILE%%`, `%%MAX_GROUPS%%`, `%%MIN_COUNT%%`, `%%SESSION_PATH%%`, `%%ATTACH_LIB_VBS%%`. | | `<SAP_DEV_CORE_SHARED_DIR>/scripts/sap_keyed_diff_lib.ps1` | The ONE keyed row-diff engine (`Get-SapKeyedDiff` / `Write-SapKeyedDiffTsv`), shared with /sap-config-compare + /sap-compare `--table-content`. |

---

Step 0 — Resolve Work Directory

**Resolve `work_dir` via the env-aware helper** — do NOT take `work_dir` from a direct `settings.json` read (that ignores the `SAPDEV_AI_WORK_DIR` env var and `userconfig.json`). Use the `WORK_DIR=` value printed by:

powershell -NoProfile -ExecutionPolicy Bypass -Command ". '<SAP_DEV_CORE_SHARED_DIR>\scripts\sap_settings_lib.ps1'; . '<SAP_DEV_CORE_SHARED_DIR>\scripts\sap_connection_lib.ps1'; Write-Output ('WORK_DIR=' + (Get-SapWorkDir)); Write-Output ('RUN_TEMP=' + (Get-SapRunTemp))"

The settings note below still applies to the OTHER keys.

**Settings reads/writes follow `shared/rules/settings_lookup.md`** — merge per-key on the `.value` field (env var → `settings.local.json` → `userconfig.json` → `settings.json`); non-per-connection writes go to `userconfig.json`. Resolve sap-dev-core paths: 2 levels up from `<SKILL_DIR>` to the plugin root, then `settings.json` and (if present) `settings.local.json`. Read `custom_url`.

| Setting | Default if blank | |---|---| | `work_dir` | `C:\sap_dev_work` | | `custom_url` | `{work_dir}\custom` |

Set `{WORK_TEMP}` = `{work_dir}\temp`

Ensure the temp directory exists:

cmd /c if not exist "{WORK_TEMP}" mkdir "{WORK_TEMP}"

Set `{RUN_TEMP}` = the `RUN_TEMP=` value printed above — a fresh per-run scratch directory `{work_dir}\temp\run_<id>`, already created by `Get-SapRunTemp`. Resolve it **once here** and reuse the same value for the rest of this invocation; it isolates this run's generated wrappers / state / scratch files so concurrent runs (parallel sub-agents, multi-connection deploys) never collide. **`{WORK_TEMP}` stays the base temp dir** and is used ONLY for `Get-SapCurrentSessionPath -WorkTemp '{WORK_TEMP}'` (the session-attach plumbing derives `{work_dir}\runtime` from its parent, so it must see the base path, not the run dir). Everything the skill writes itself goes under `{RUN_TEMP}`.

---

Step 0.5 — Start Logging

Start a structured log run. State file: `{RUN_TEMP}\sap_se16n_run.json`. Best-effort.

powershell -ExecutionPolicy Bypass -File "<SAP_DEV_CORE_SHARED_DIR>\scripts\sap_log_helper.ps1" -Action start -StateFile "{RUN_TEMP}\sap_se16n_run.json" -Skill sap-se16n -ParamsJson "{\"table\":\"<TABLE>\"}"

---

Step 1 — Collect Parameters

| Parameter | Description | Example | |---|---|---| | Table name | SAP transparent / pooled / cluster table | `T001` | | Filter fields | Zero or more `field op value(s)` triples — see operator table | `LAND1 IN CN,JP` | | Select fields | Optional comma-separated list of output columns; empty = all fields | `BUKRS,BUTXT,LAND1,WAERS` | | Ou