Resolves PR #272 review #10/P5. The --if-add-node-id / -node-summary /
-doc-description / -node-text args were store_true, which rejected the
documented yes/no values and left default-on options impossible to disable
from the CLI. They now use nargs='?' + const=True + a yes/no-coercing type:
--if-add-node-id -> on
--if-add-node-id no -> off (legacy form still works)
(omitted) -> use the IndexConfig default
README updated to the flag usage (noting the legacy `no` off-switch), and
--if-add-node-text is now documented too.
Decisions from the review:
- #7 (api_key semantics): verified FALSE POSITIVE — 0.2.x is a cloud SDK whose
api_key is a PageIndex cloud key (cloud_api.LegacyCloudAPI + docs.pageindex.ai/sdk),
matching the new SDK. No change.
- #11 (if_add_doc_description default True): kept intentionally (open mode).
Claude-Session: https://claude.ai/code/session_01Kx5DgKbhK1N8autqXH8SmS
Verified against current dev; the compat/behavior decisions (#7 api_key
semantics, #10 CLI flags, #11 doc-description default) are deferred.
Crashes:
- page_index(): snapshot args before importing IndexConfig — locals() was
capturing the imported class and IndexConfig(extra='forbid') made every call
raise ValidationError.
- process_none_page_numbers: pop('page', None) instead of del (a TOC item
without 'page' raised KeyError mid-pipeline).
- pipeline._run_async: guard only the loop detection, not the run, so a real
RuntimeError from the coroutine isn't masked as "asyncio.run() cannot be
called from a running event loop".
Silent-wrong / robustness:
- LocalBackend.get_document_structure and the agent get_document /
get_document_structure tools now surface a missing doc (raise / error-JSON)
instead of returning empty, matching get_page_content and the cloud backend.
- cloud delete_collection drops the cached folder_id.
- cloud query raises on an empty collection instead of POSTing doc_id:[].
- LocalClient skips the API-key check for keyless providers (ollama, lm_studio,
…) so keyless LiteLLM models aren't rejected at construction.
Compat / cleanup:
- md_to_tree coerces legacy 'yes'/'no' string flags (a bare 'no' was truthy).
- FileTypeError also subclasses ValueError (0.2.x raised ValueError).
- _validate_llm_provider no longer mutates global litellm.model_cost_map_url.
- __all__ re-includes legacy exports (page_index, md_to_tree, get_*).
- Rewrite examples/agentic_vectorless_rag_demo.py to the Collection API and use
the in-repo attention.pdf (the old workspace=/client.index/client.documents
API no longer exists).
Adds tests/test_review_fixes.py (10 regressions). Full suite: 189 passed.
Claude-Session: https://claude.ai/code/session_01Kx5DgKbhK1N8autqXH8SmS
