fix: Aug 18-19 review hardening — five max-effort rounds across tools, chat, and flash

.github/workflows/tests.yml

@@ -30,6 +30,9 @@ jobs:
           python-version: ${{ matrix.python-version }}
           cache: pip
       - run: pip install -r requirements.txt pytest
+      - if: matrix.agent-frameworks == 'without'
+        # requirements.txt carries it; this leg tests the no-framework paths
+        run: pip uninstall -y openai-agents
       - if: matrix.agent-frameworks == 'with'
         run: pip install openai-agents claude-agent-sdk anthropic
       - run: python -m pytest -q

.gitignore

@@ -6,4 +6,3 @@ __pycache__
 logs/
 .pageindex/
 dist/
-*.doc_id

README.md

@@ -173,7 +173,7 @@ python3 run_pageindex.py --pdf_path /path/to/your/document.pdf
 <details>
 <summary>Optional parameters</summary>
 <br>
-You can customize the processing with additional optional arguments (the structure-tuning flags below require <code>--mode standard</code>):
+You can customize the processing with additional optional arguments (the structure-tuning flags from <code>--toc-check-pages</code> down require <code>--mode standard</code>):
 
 ```
 --mode                  Processing mode: flash (default) or standard

examples/agentic_vectorless_rag_demo.py

@@ -32,14 +32,13 @@
 from agents.stream_events import RawResponsesStreamEvent, RunItemStreamEvent
 from openai.types.responses import ResponseTextDeltaEvent, ResponseReasoningSummaryTextDeltaEvent
 
-from pageindex import PageIndexAPIError, PageIndexLocalClient
+from pageindex import PageIndexLocalClient
 import pageindex.utils as utils
 
 PDF_URL = "https://arxiv.org/pdf/2603.15031"
 
 _EXAMPLES_DIR = Path(__file__).parent
 PDF_PATH = _EXAMPLES_DIR / "documents" / "attention-residuals.pdf"
-DOC_ID_PATH = _EXAMPLES_DIR / "documents" / "attention-residuals.doc_id"
 STORAGE_PATH = _EXAMPLES_DIR / ".pageindex"
 
 
@@ -127,27 +126,13 @@ async def _run():
     print("=" * 60)
     print("Step 1: Index PDF and view tree structure")
     print("=" * 60)
-    doc_id = None
-    if DOC_ID_PATH.exists():
-        cached = DOC_ID_PATH.read_text().strip()
-        try:
-            client.get_document(cached)
-            doc_id = cached
-        except PageIndexAPIError:
-            DOC_ID_PATH.unlink()
-    if doc_id is None:
-        # The .doc_id cache is gitignored — on a fresh clone with an
-        # existing store, find the already-indexed copy by name instead of
-        # re-indexing it.
-        doc_id = next(
-            (doc["id"] for doc in client.list_documents(limit=100)["documents"]
-             if doc["name"] == PDF_PATH.name), None)
+    doc_id = next(
+        (doc["id"] for doc in client.list_documents(limit=100)["documents"]
+         if doc["name"] == PDF_PATH.name), None)
     if doc_id:
-        DOC_ID_PATH.write_text(doc_id)
         print(f"\nLoaded cached doc_id: {doc_id}")
     else:
         doc_id = client.submit_document(str(PDF_PATH), wait=True)["doc_id"]
-        DOC_ID_PATH.write_text(doc_id)
         print(f"\nIndexed. doc_id: {doc_id}")
     print("\nTree Structure (top-level sections):")
     structure = client.get_tree(doc_id, node_summary=True)["result"]

pageindex/__init__.py

@@ -1,11 +1,6 @@
 """PageIndex SDK."""
-import os as _os
 from typing import TYPE_CHECKING as _TYPE_CHECKING
 
-# LiteLLM's import otherwise fetches its model map over the network — seconds
-# of blocking (or a hang offline). setdefault, so an explicit user choice wins.
-_os.environ.setdefault("LITELLM_LOCAL_MODEL_COST_MAP", "True")
-
 from .client import PageIndexClient, PageIndexCloudClient, PageIndexLocalClient
 from .errors import PageIndexAPIError
 
@@ -23,8 +18,6 @@
 ]
 
 _LAZY = {
-    "page_index": ".page_index_classic",
-    "page_index_main": ".page_index_classic",
     "page_index_flash": ".flash",
     "optimize_tree": ".tree_optimize",
     "md_to_tree": ".page_index_md",
@@ -34,25 +27,18 @@
                "mcp_bridge", "page_index_classic", "page_index_md",
                "tree_optimize", "utils"}
 
+
 def __getattr__(name):
     if name.startswith("_"):
-        # Dunder probes (copy, pickle, inspect) are the frequent unknown
-        # names — they must not trigger the classic import below.
         raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
     import importlib
     if name in _SUBMODULES:
         return importlib.import_module(f".{name}", __name__)
-    # Pre-0.2.10 compat: unknown names fall through to the classic module,
-    # whose public surface (ConfigLoader, count_tokens, ...) resolved as
-    # package attributes. A non-underscore typo pays one classic import
-    # before its AttributeError — not worth an allowlist.
-    module = importlib.import_module(_LAZY.get(name, ".page_index_classic"),
-                                     __name__)
+    module = importlib.import_module(_LAZY.get(name, ".page_index_classic"), __name__)
     try:
         value = getattr(module, name)
     except AttributeError:
-        raise AttributeError(
-            f"module {__name__!r} has no attribute {name!r}") from None
+        raise AttributeError(f"module {__name__!r} has no attribute {name!r}") from None
     globals()[name] = value
     return value