feat: v2.2.0 — agentdb v1.3 + persisted schema with agent context#16
Merged
Conversation
- Bump @backloghq/agentdb from 1.2.1 to 1.3.0, unlocking persisted schemas with agent context, the schema lifecycle toolset, the $strLen filter operator, and schema bootstrap. - Enrich taskSchema with top-level description and instructions plus per-field description on every schema-declared field. Auto-persists to meta/tasks.schema.json on first open so any agent connecting to the backlog MCP server can call db_get_schema and discover the collection's shape + usage guidance without reading source. - Declare schema version: 1 for future evolution tracking. - Bump plugin.json + marketplace.json to 2.2.0 and strip hardcoded tool/skill counts from their descriptions. - README: drop stale '24 tools' and '(189 tests)' counts — descriptive text only.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Backlog v2.2.0 rides on agentdb v1.3. The main story: the
taskscollection now carries agent-facing context (description, instructions, per-field descriptions) that auto-persists tometa/tasks.schema.jsonon first open. Any agent connecting to the backlog MCP server can calldb_get_schemaand discover the shape + usage semantics of the tasks collection without reading this repo's source.What's new
Upgraded
@backloghq/agentdb1.2.1 → 1.3.0Unlocks the v1.3 feature set for backlog's data directory:
db_get_schema,db_set_schema,db_delete_schema,db_diff_schema,db_migrate,db_infer_schema)$strLenfilter operator (available in both JSON and compact syntax)schemas/*.jsonfiles or use--schemas <glob>Collection.iterate()streaming generator_agentaudit stamp)Enriched
taskSchemadescription— what the tasks collection is for, as seen by any connecting agentinstructions— status flow, how to usedepends, date semantics, recurrence notes,has_docmeaningversion: 1— tracked against the persisted file for future schema evolutiondescriptionon every schema-declared field (id,description,status,priority,project, dates,tags,depends,recur,agent, timestamps,parent,has_doc)On first open after the upgrade, backlog auto-persists the task schema to
<taskdataRoot>/<project>/meta/tasks.schema.json. No migration step required.Plugin + marketplace version
Both
.claude-plugin/plugin.jsonand.claude-plugin/marketplace.jsonbumped to2.2.0. Descriptions rewritten to avoid hardcoded tool/skill counts.Test plan
meta/after first tool call)