Commit graph

5 commits

Author SHA1 Message Date
Yiorgis Gozadinos
09a7076b7e
State what the code does, not what it replaced
Comments and docstrings across the branch narrated rejected
alternatives, consequences and history; each now states the current
contract. Renames test_a_legacy_uri_client_keeps_its_error to
test_an_unnamed_database_keeps_its_error. Documents the Sandbox
connection paths, the citation header's database segment, both
AmbiguousDatabaseError conditions on create_app, and run_inspector's
scope parameter. Doc paragraphs added by the branch in python.md,
storage.md and cli.md are one physical line each.
2026-08-28 15:13:52 +03:00
Yiorgis Gozadinos
0dec3d4e63
Make three tests assert what they are about
`test_an_image_query_builds_no_reranker` never submitted an image query: it
opened clients and found nothing built, which is lazy construction. It sends one
now, so consulting the reranker before the query type fails it.

`TestComparingEmbedders` called `_require_one_embedder` and asserted nothing.
It rejects a disagreement and accepts an absent record, and searches through.

Three `ModelRetry` tests took any reason where the reason is the subject.
2026-08-27 18:04:28 +03:00
Yiorgis Gozadinos
87367759f9
Say what makes a cited chunk id ambiguous
The documented rule was existence in more than one selected database. The rule
is narrower and does not need to be wider: a copy the search never returned
grounded nothing, so the retrieved result is the citation and its database is
recorded rather than guessed.

The page now states the whole rule, including the fallback's own check for an
id no search returned. Two retrieved copies are refused, and so is an id
already cited from another database in the conversation. The case between them
had no test.
2026-08-27 14:09:01 +03:00
Yiorgis Gozadinos
b8bf846bb7
Cite a repeated chunk from its last occurrence
Collision detection replaced the lookup's dict comprehension with
`setdefault`, which also flipped a chunk found by several searches from its
last occurrence to its first. The copies differ in everything the expansion
window decides, figures included, so that silently changed what a citation
renders.

The rules are separate now: a repeated (source, chunk_id) takes the later
result, a chunk_id under two sources is still refused.
2026-08-27 13:25:06 +03:00
Yiorgis Gozadinos
ca2e28559e
Split the multi-database tests by subject
Two files of 1,405 and 814 lines become seven: scope resolution, lifecycle,
search, documents, expansion, citations and capabilities. `_config`, `_seed`
and the rest move to `helpers.py`, importable by the sandbox tests that share
them, and the package points VCR back at `tests/cassettes/multi_db/`.
2026-08-26 13:43:53 +03:00