feat(collection): doc_ids accepts str|list, design cleanups

- Collection.query and Backend.query/query_stream accept doc_ids as
  str, list[str] or None. Single str is normalized to [str] inside each
  backend; bare [] is rejected with ValueError at both layers.
- wrap_with_doc_context wraps the scoped doc list in <docs>...</docs>
  and SCOPED_SYSTEM_PROMPT instructs the agent to treat that block as
  data, not instructions (defense against prompt injection via
  auto-generated doc_description).
- _require_cloud_api now distinguishes api_key="" from api_key=None;
  the former gives a targeted error pointing at the empty-string vs
  fall-back-to-local situation when legacy SDK methods are called.
- Legacy PageIndexClient.list_documents docstring spells out the
  return-shape difference vs collection.list_documents() to flag a
  silent migration footgun (paginated dict with id/name keys vs plain
  list[dict] with doc_id/doc_name keys).
- Remove dead CloudBackend.get_agent_tools stub (not on the Backend
  protocol; only ever returned an empty AgentTools()) and the
  SYSTEM_PROMPT alias (OPEN_/SCOPED_SYSTEM_PROMPT are the explicit
  names now).
- README quick start and streaming example now pass doc_ids; new
  multi-document section shows both str and list forms.
- examples/demo_query_modes.py exercises all five query-mode cases
  (single-doc, multi-doc with/without env var, scoped single, scoped
  multi) for manual verification.
This commit is contained in:
mountain 2026-05-15 17:03:17 +08:00
parent d7b36aaf3f
commit a47c36a3f5
13 changed files with 322 additions and 45 deletions

View file

@ -111,7 +111,8 @@ def test_wrap_with_doc_context_single(populated_backend):
docs = populated_backend._scoped_docs("papers", ["d1"])
wrapped = wrap_with_doc_context(docs, "what is this?")
assert "d1: alpha.pdf — About alpha." in wrapped
assert "specified the following document:" in wrapped
assert "specified the following document" in wrapped
assert "<docs>" in wrapped and "</docs>" in wrapped
assert "User question: what is this?" in wrapped
@ -121,10 +122,22 @@ def test_wrap_with_doc_context_multi(populated_backend):
wrapped = wrap_with_doc_context(docs, "compare them")
assert "d1: alpha.pdf — About alpha." in wrapped
assert "d2: beta.pdf — About beta." in wrapped
assert "specified the following documents:" in wrapped
assert "specified the following documents" in wrapped
assert "<docs>" in wrapped and "</docs>" in wrapped
assert "User question: compare them" in wrapped
def test_scoped_docs_raises_on_missing(populated_backend):
with pytest.raises(DocumentNotFoundError, match="nonexistent"):
populated_backend._scoped_docs("papers", ["d1", "nonexistent"])
def test_normalize_doc_ids():
assert LocalBackend._normalize_doc_ids("d1") == ["d1"]
assert LocalBackend._normalize_doc_ids(["d1", "d2"]) == ["d1", "d2"]
assert LocalBackend._normalize_doc_ids(None) is None
def test_normalize_doc_ids_rejects_empty_list():
with pytest.raises(ValueError, match="cannot be empty"):
LocalBackend._normalize_doc_ids([])