@josephyan/qingflow-cli 1.0.10 → 1.0.11

package/README.md

@@ -3,13 +3,13 @@
 Install:
 
 ```bash
-npm install @josephyan/qingflow-cli@1.0.10
+npm install @josephyan/qingflow-cli@1.0.11
 ```
 
 Run:
 
 ```bash
-npx -y -p @josephyan/qingflow-cli@1.0.10 qingflow
+npx -y -p @josephyan/qingflow-cli@1.0.11 qingflow
 ```
 
 Environment:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@josephyan/qingflow-cli",
-  "version": "1.0.10",
+  "version": "1.0.11",
   "description": "Human-friendly Qingflow command line interface for auth, record operations, import, tasks, and stable builder flows.",
   "license": "MIT",
   "type": "module",

package/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "qingflow-mcp"
-version = "1.0.10"
+version = "1.0.11"
 description = "User-authenticated MCP server for Qingflow"
 readme = "README.md"
 license = "MIT"
@@ -29,6 +29,7 @@ dependencies = [
   "openpyxl>=3.1,<4.0",
   "pydantic>=2.8,<3.0",
   "pycryptodome>=3.20,<4.0",
+  "pypdf>=5.0,<6.0",
   "python-socketio[client]>=5.11,<6.0",
 ]
 

package/src/qingflow_mcp/cli/commands/record.py

@@ -56,7 +56,6 @@ def register(subparsers: argparse._SubParsersAction[argparse.ArgumentParser]) ->
     list_parser.add_argument("--query-fields-file")
     list_parser.add_argument("--where-file")
     list_parser.add_argument("--order-by-file")
-    list_parser.add_argument("--limit", type=int, default=20)
     list_parser.add_argument("--page", type=int, default=1)
     list_parser.add_argument("--view-id")
     list_parser.add_argument("--list-type", dest="legacy_list_type", type=int, help=argparse.SUPPRESS)
@@ -248,7 +247,6 @@ def _handle_list(args: argparse.Namespace, context: CliContext) -> dict:
         query_fields=_query_fields(args),
         where=load_list_arg(args.where_file, option_name="--where-file"),
         order_by=load_list_arg(args.order_by_file, option_name="--order-by-file"),
-        limit=args.limit,
         page=args.page,
         view_id=args.view_id,
     )

package/src/qingflow_mcp/cli/formatters.py

@@ -190,20 +190,9 @@ def _format_record_list(result: dict[str, Any]) -> str:
         lines.append(f"- query: {lookup.get('query')}")
         lines.append(f"- confidence: {lookup.get('confidence')}")
         lines.append(f"- next_action: {lookup.get('next_action')}")
-        lines.append(f"- reported_total: {lookup.get('reported_total')}")
-        candidates = lookup.get("candidates") if isinstance(lookup.get("candidates"), list) else []
-        for candidate in candidates[:5]:
-            if not isinstance(candidate, dict):
-                continue
-            title = candidate.get("title") or "-"
-            record_id = candidate.get("record_id") or "-"
-            score = candidate.get("score")
-            lines.append(f"  - {record_id} | score={score} | {title}")
-            matches = candidate.get("matched_fields") if isinstance(candidate.get("matched_fields"), list) else []
-            if matches:
-                match = matches[0]
-                if isinstance(match, dict):
-                    lines.append(f"    match: {match.get('title')}={match.get('value')}")
+        lines.append(f"- total_count: {lookup.get('total_count')}")
+        lines.append(f"- returned_count: {lookup.get('returned_count')}")
+        lines.append(f"- truncated: {lookup.get('truncated')}")
     lines.append(f"Returned Records: {len(items)}")
     for item in items[:10]:
         if isinstance(item, dict):
@@ -256,6 +245,15 @@ def _format_record_get(result: dict[str, Any]) -> str:
     media_items = media_assets.get("items") if isinstance(media_assets.get("items"), list) else []
     downloaded_media = [item for item in media_items if isinstance(item, dict) and item.get("access_status") == "downloaded"]
     failed_media = [item for item in media_items if isinstance(item, dict) and item.get("access_status") != "downloaded"]
+    file_assets = result.get("file_assets") if isinstance(result.get("file_assets"), dict) else {}
+    file_items = file_assets.get("items") if isinstance(file_assets.get("items"), list) else []
+    downloaded_files = [item for item in file_items if isinstance(item, dict) and item.get("access_status") == "downloaded"]
+    failed_files = [item for item in file_items if isinstance(item, dict) and item.get("access_status") != "downloaded"]
+    extracted_files = [
+        item
+        for item in downloaded_files
+        if isinstance(item.get("extraction"), dict) and item["extraction"].get("status") == "ok"
+    ]
     associated_resources = result.get("associated_resources") if isinstance(result.get("associated_resources"), list) else []
     unavailable_context = result.get("unavailable_context") if isinstance(result.get("unavailable_context"), list) else []
     lines = [
@@ -267,17 +265,26 @@ def _format_record_get(result: dict[str, Any]) -> str:
         f"Data logs: {data_logs.get('status') or '-'} / loaded={data_logs.get('items_loaded')}",
         f"Workflow logs: {workflow_logs.get('status') or '-'} / loaded={workflow_logs.get('items_loaded')}",
         f"Media assets: {media_assets.get('status') or '-'} / downloaded={len(downloaded_media)} / failed={len(failed_media)}",
+        f"File assets: {file_assets.get('status') or '-'} / downloaded={len(downloaded_files)} / extracted={len(extracted_files)} / failed={len(failed_files)}",
         f"Associated resources: {len(associated_resources)}",
         f"Unavailable contexts: {len(unavailable_context)}",
     ]
     if media_assets.get("local_dir"):
         lines.append(f"Media dir: {media_assets.get('local_dir')}")
+    if file_assets.get("local_dir"):
+        lines.append(f"File dir: {file_assets.get('local_dir')}")
     if failed_media:
         failure_counts: dict[str, int] = {}
         for item in failed_media:
             key = f"{item.get('access_status') or 'unknown'} via {item.get('download_strategy') or 'unknown'}"
             failure_counts[key] = failure_counts.get(key, 0) + 1
         lines.append("Media failures: " + ", ".join(f"{key}={count}" for key, count in sorted(failure_counts.items())))
+    if failed_files:
+        failure_counts = {}
+        for item in failed_files:
+            key = f"{item.get('access_status') or 'unknown'} via {item.get('download_strategy') or 'unknown'}"
+            failure_counts[key] = failure_counts.get(key, 0) + 1
+        lines.append("File failures: " + ", ".join(f"{key}={count}" for key, count in sorted(failure_counts.items())))
     summary = result.get("summary") if isinstance(result.get("summary"), dict) else {}
     if summary.get("text"):
         lines.append(f"Summary: {summary.get('text')}")

package/src/qingflow_mcp/response_trim.py

@@ -427,7 +427,7 @@ def _trim_detail_context_record_get(payload: JSONObject) -> None:
     _trim_item_list(
         payload,
         "fields",
-        allowed=("field_id", "title", "type", "value", "display_value", "requested_focus", "asset_ids"),
+        allowed=("field_id", "title", "type", "value", "display_value", "requested_focus", "asset_ids", "file_asset_ids"),
     )
     references = payload.get("references")
     if isinstance(references, list):
@@ -450,7 +450,7 @@ def _trim_detail_context_record_get(payload: JSONObject) -> None:
             target_fields = item.get("target_fields") if isinstance(item.get("target_fields"), list) else []
             if target_fields:
                 compact["target_fields"] = [
-                    _pick(field, ("field_id", "title", "type", "value", "display_value", "asset_ids"))
+                    _pick(field, ("field_id", "title", "type", "value", "display_value", "asset_ids", "file_asset_ids"))
                     for field in target_fields
                     if isinstance(field, dict)
                 ]
@@ -484,6 +484,37 @@ def _trim_detail_context_record_get(payload: JSONObject) -> None:
             if isinstance(item, dict)
         ]
         payload["media_assets"] = compact_media
+    file_assets = payload.get("file_assets")
+    if isinstance(file_assets, dict):
+        compact_files = _pick(file_assets, ("status", "local_dir", "warnings"))
+        items = file_assets.get("items") if isinstance(file_assets.get("items"), list) else []
+        compact_files["items"] = [
+            _pick(
+                item,
+                (
+                    "file_asset_id",
+                    "media_asset_id",
+                    "kind",
+                    "source",
+                    "field_id",
+                    "field_title",
+                    "file_name",
+                    "local_path",
+                    "access_status",
+                    "readable_by_agent",
+                    "mime_type",
+                    "size_bytes",
+                    "download_strategy",
+                    "storage_auth_type",
+                    "storage_cookie_prefix",
+                    "redirected",
+                    "extraction",
+                ),
+            )
+            for item in items
+            if isinstance(item, dict)
+        ]
+        payload["file_assets"] = compact_files
     for key in ("data_logs", "workflow_logs"):
         node = payload.get(key)
         if not isinstance(node, dict):
@@ -519,17 +550,15 @@ def _trim_record_list(payload: JSONObject) -> None:
     if not isinstance(data, dict):
         return
     pagination = data.get("pagination") if isinstance(data.get("pagination"), dict) else {}
-    returned_items = pagination.get("returned_items")
-    result_amount = pagination.get("result_amount")
-    limit = pagination.get("limit")
-    truncated = False
-    if isinstance(result_amount, int) and isinstance(returned_items, int):
+    returned_items = pagination.get("returned_count", pagination.get("returned_items"))
+    result_amount = pagination.get("total_count", pagination.get("result_amount"))
+    truncated = bool(pagination.get("truncated"))
+    if not truncated and isinstance(result_amount, int) and isinstance(returned_items, int):
         truncated = result_amount > returned_items
     compact_pagination = {
         "loaded": True,
-        "page_size": limit,
-        "fetched_pages": 1,
-        "reported_total": result_amount,
+        "returned_count": returned_items,
+        "total_count": result_amount,
         "truncated": truncated,
     }
     selection = data.get("selection") if isinstance(data.get("selection"), dict) else {}
@@ -544,33 +573,14 @@ def _trim_record_list(payload: JSONObject) -> None:
     payload["data"] = compact
     lookup = payload.get("lookup") if isinstance(payload.get("lookup"), dict) else {}
     if lookup:
-        candidates = lookup.get("candidates") if isinstance(lookup.get("candidates"), list) else []
         payload["lookup"] = {
             "mode": lookup.get("mode"),
             "query": lookup.get("query"),
-            "reported_total": lookup.get("reported_total"),
-            "returned_candidates": lookup.get("returned_candidates"),
+            "total_count": lookup.get("total_count", lookup.get("reported_total")),
+            "returned_count": lookup.get("returned_count"),
+            "truncated": lookup.get("truncated"),
             "confidence": lookup.get("confidence"),
             "next_action": lookup.get("next_action"),
-            "candidates": [
-                {
-                    "record_id": candidate.get("record_id"),
-                    "title": candidate.get("title"),
-                    "score": candidate.get("score"),
-                    "matched_fields": [
-                        _pick(match, ("title", "value", "match_type", "score"))
-                        for match in (candidate.get("matched_fields") if isinstance(candidate.get("matched_fields"), list) else [])
-                        if isinstance(match, dict)
-                    ],
-                    "display_fields": [
-                        _pick(field, ("title", "value"))
-                        for field in (candidate.get("display_fields") if isinstance(candidate.get("display_fields"), list) else [])
-                        if isinstance(field, dict)
-                    ],
-                }
-                for candidate in candidates[:5]
-                if isinstance(candidate, dict)
-            ],
         }
 
 

package/src/qingflow_mcp/server.py

@@ -69,7 +69,7 @@ Call `record_import_schema_get` when the import field mapping is unclear before
 `record_insert_schema_get` returns the current user's insert-ready applicant schema; read `required_fields`, `optional_fields`, `runtime_linked_required_fields`, and `payload_template`.
 `record_update_schema_get` returns the current record's overall update-ready writable field set across matched accessible views; read `writable_fields` and `payload_template`.
 `record_browse_schema_get(view_id=...)` returns the same readable fields shown in the selected Qingflow table view header.
-`record_access.fields` and CSV columns use that exact same view schema.
+`record_access.fields` / CSV columns and `record_list.columns / where / order_by / query_fields` use that exact same view schema.
 `record_code_block_schema_get` returns code-block-ready schema for exact code block field selection.
 `record_import_schema_get` returns import-ready column metadata.
 
@@ -124,8 +124,8 @@ Analysis answers must include concrete numbers. When applicable, include percent
 - `linkage.kind=logic_visibility` means linked visibility or option-driven rules are involved; `linkage.kind=reference_fill` means reference/default matching logic is involved; `linkage.kind=formula_fill` means formula/default auto-fill logic is involved.
 - `record_update_schema_get` exposes the overall writable field set for the record, but not every field combination is guaranteed; `record_update` still needs one single matched accessible view that can cover the payload.
 - `record_delete` deletes by `record_id` or `record_ids`.
-- `record_get` is the single-record frontend detail context tool. It returns detail-page visible fields, one-level relation targets, first-page data/workflow logs, associated views/reports, local readable image assets from rich text/attachments/image fields/subtables/reference targets, unavailable context, and `semantic_context`.
-- Read record images from `record_get.media_assets.items[].local_path` when `readable_by_agent=true`; `record_get` follows the frontend storage cookie redirect path for Qingflow attachments, and remote file URLs should not be treated as directly readable.
+- `record_get` is the single-record frontend detail context tool. It returns detail-page visible fields, one-level relation targets, first-page data/workflow logs, associated views/reports, local readable image assets, local downloadable file assets, unavailable context, and `semantic_context`.
+- Read record images from `record_get.media_assets.items[].local_path` when `readable_by_agent=true`; read attachments/documents/tables from `record_get.file_assets.items[].local_path` and `extraction.text_path` when present. `record_get` follows the frontend storage cookie redirect path for Qingflow attachments, and remote file URLs should not be treated as directly readable.
 - `record_get.columns` are focus hints only; they do not project the detail fields. Read facts from top-level `fields[]`.
 - When readback shape matters after insert or update, prefer `record_get` for human/detail-page context, or `record_list(..., output_profile="normalized")` for batch-shaped normalized rows.
 

package/src/qingflow_mcp/server_app_user.py

@@ -61,7 +61,7 @@ Call `record_import_schema_get` when the import field mapping is unclear before
 Inside `optional_fields`, any field with `may_become_required=true` is still writable, but may become required when linked visibility or option-driven runtime rules activate.
 `record_update_schema_get` returns the current record's overall update-ready writable field set across matched accessible views; read `writable_fields` and `payload_template`.
 `record_browse_schema_get(view_id=...)` returns the same readable fields shown in the selected Qingflow table view header.
-`record_access.fields` and CSV columns use that exact same view schema; a missing field means it is not readable in that view.
+`record_access.fields` / CSV columns and `record_list.columns / where / order_by / query_fields` use that exact same view schema; a missing field means it is not readable in that view.
 `searchQueIds` is a backend full-text search scope, not an output-column/projection mechanism.
 `record_code_block_schema_get` returns code-block-ready schema for exact code block field selection.
 `record_import_schema_get` returns import-ready column metadata.
@@ -125,8 +125,8 @@ Analysis answers must include concrete numbers. When applicable, include percent
 - `linkage.kind=logic_visibility` means linked visibility or option-driven rules are involved; `linkage.kind=reference_fill` means reference/default matching logic is involved; `linkage.kind=formula_fill` means formula/default auto-fill logic is involved.
 - `record_update_schema_get` exposes the overall writable field set for the record, but not every field combination is guaranteed; `record_update` still needs one single matched accessible view that can cover the payload.
 - `record_delete` deletes by `record_id` or `record_ids`.
-- `record_get` is the single-record frontend detail context tool. It returns detail-page visible fields, one-level relation targets, first-page data/workflow logs, associated views/reports, local readable image assets from rich text/attachments/image fields/subtables/reference targets, unavailable context, and `semantic_context`.
-- Read record images from `record_get.media_assets.items[].local_path` when `readable_by_agent=true`; `record_get` follows the frontend storage cookie redirect path for Qingflow attachments, and remote file URLs should not be treated as directly readable.
+- `record_get` is the single-record frontend detail context tool. It returns detail-page visible fields, one-level relation targets, first-page data/workflow logs, associated views/reports, local readable image assets, local downloadable file assets, unavailable context, and `semantic_context`.
+- Read record images from `record_get.media_assets.items[].local_path` when `readable_by_agent=true`; read attachments/documents/tables from `record_get.file_assets.items[].local_path` and `extraction.text_path` when present. `record_get` follows the frontend storage cookie redirect path for Qingflow attachments, and remote file URLs should not be treated as directly readable.
 - `record_get.columns` are focus hints only; they do not project the detail fields. Read facts from top-level `fields[]`.
 - When readback shape matters after insert or update, prefer `record_get` for human/detail-page context, or `record_list(..., output_profile="normalized")` for batch-shaped normalized rows.