Repository navigation
Explain repository tags when agents save code-related facts - #787
Merged
Merged
Conversation
Manual memory writes need the repository tag to resolve code links from a personal namespace. Scope the guidance to facts about the current repository so other facts keep their own scope. Signed-off-by: zlareb1 <lareb.zafar@clickhouse.com>
zlareb1
force-pushed
the
fix/plugin-memory-code-guidance
branch
from
November 18, 2026 06:21
0663fb7 to
aa38902
Compare
The repository-tag wording changes these reviewed body-builder files without changing request construction. Renew only their source pins after auditing the sender paths; keep exception entries and the guard unchanged. Signed-off-by: zlareb1 <lareb.zafar@clickhouse.com>
7 of 8 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Changelog category (leave one):
Changelog entry
The coding-agent primer and memory tool descriptions explain how to tag repository-specific facts without tagging unrelated facts.
Why
Hook captures carry a repository tag, but a manually saved repository fact needs the caller to supply that tag. The primer and memory tool descriptions give the same instruction so repository-filtered recall can find those facts. Personal facts stay in the caller's own namespace.
Scope and risk
Changes the session primer, the default and atomic memory tool descriptions, and their checks. Both plugin manifests use version 1.2.29. The generated plugin copy matches its source. The two reviewed-source hashes for the mirrored primer libraries are renewed after auditing their sender paths and request builders. All 85 exception entries and the other 41 reviewed-source hashes remain unchanged; the guard and collector are unchanged.
This change targets
mainindependently of the endpoint configuration change. It changes no plugin skills, endpoint resolution, write handler or authorization rule. Tags remain caller-supplied. The integration regression checks that a manually tagged memory links to code while an untagged memory does not, and checks the stored identity tuple and provenance.Compatibility, rollout and rollback
Tests
AI assistance in the code (leave one; writing this description with AI is fine):
AI-generated (an agent wrote most of the diff): Codex checked the guidance against the tagging and code-link contracts, replayed the guidance commit independently, and ran the static checks above.
I can explain every line of this diff and how it interacts with the rest of Loom.
Checklist