Repository navigation
feat(protocols): recognize Deep Agents protocol skill activation - #35
Closed
sriaradhyula wants to merge 1 commit into
Closed
sriaradhyula wants to merge 1 commit into
sriaradhyula wants to merge 1 commit into
Conversation
Signed-off-by: Sri Aradhyula <sraradhy@cisco.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Deep Agents advertises released accord-/concord- skill names and loads instructions with read_file. The detector currently recognizes only legacy l9-* names and explicit activation/script tools, so actual skill loads remain invisible.
Keep legacy prefixes and accept released names. Count a successful read_file only when its exact /skills/.../SKILL.md path was advertised in the same agent's system catalog. Failed reads, another agent's catalog and unadvertised paths do not count. This proves instructions loaded, not script execution or protocol completion; script-level metric requirements remain unchanged.
Validation: all 52 cognition-protocols worker tests pass, including eight cases for both protocols covering successful/failed reads, missing catalogs and wrong-agent reads. Ruff E/F checks and diff checks pass. The matching CAIPE exporter sends only catalog metadata and matching file paths. A new worker image must be published/promoted before canary acceptance.
Prepared with Codex. Commits carry the human-provided Signed-off-by.