Add bounded knowledge retrieval (#179)

* Add bounded knowledge retrieval

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Copilot-Session: 0d8b7764-f15a-49ea-8d50-d9147334f8af

* Fix bc-version overflow and pathless-row identity in bounded retrieval

Catalog matching compared an Int32 -BCVersion against a bigint range bound.
PowerShell coerces the right operand to the left operand's type, so a bound
wider than Int32 threw a conversion error and failed the whole domain catalog
rather than the single row. Metadata validation already accepts such bounds,
so compare as bigint on both sides.

The shared pager built its oversized-row message with $row.path, which
throws under Set-StrictMode -Version Latest when a row carries no path,
replacing the explicit bound failure with a property-lookup error. Resolve the
path defensively for dictionary and object rows so the offset-based fallback
is reachable.

Both paths gain regression coverage that fails without these fixes.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 0d8b7764-f15a-49ea-8d50-d9147334f8af
This commit is contained in:
Jesper Schulz-Wedde 2026-09-11 12:35:31 +02:00 • committed by GitHub
parent c12b2f0a88
commit 51597068b1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
26 changed files with 1891 additions and 55 deletions

View file

@ -20,7 +20,7 @@ An orchestrator invokes this skill with a `pr-diff`, `file-path`, or `folder-pat
## Source
Read the BCQuality knowledge index once — the `knowledge-index.json` BCQuality builds at the root of the knowledge checkout (Entry's preparation step regenerates it over the live, already-filtered clone — see `skills/entry.md`). It lists every article that survived layer and allow/deny filtering and carries, per article, its `path`, `layer`, `domain`, frontmatter dimensions, `keywords`, `title`, and a one-line `description` hint — exactly the fields Relevance and Worklist consume. Take the index entries whose `domain` is `testing` as this skill's candidate set across every enabled layer; do not open the individual article files at this step. Open an article's full body only once it enters the Worklist below, so a review reads the index plus the handful of worklisted articles instead of every file under `*/knowledge/testing/**`.
Use READ's **Bounded retrieval for review skills** workflow with `-Domain testing`. Consume every catalog page across enabled layers before applying this leaf's Relevance and Worklist; preserve each exact catalog path and open complete bodies only for exact paths selected by the Worklist. If the helper or prepared index is unavailable or invalid, use READ's explicit path-discovery and bounded native-read fallback.
## Relevance