Repository navigation
Conversation
Add docs/rfc-17054-llm-ranked-knowledge-advisor.md arguing the open questions on hivecommons#17054: rank-only (slug must be a matcher candidate, model reason never typed), hive-paid per-agent/fleet call caps, in-process behind phase 1's KnowledgeAdviser seam with Advise moved off the poll goroutine, pane tail + kick summary as signal, and shadow/holdout measurement through the retro lane's existing counters. Hive-Run: hivecommons#17054 Hive-Plan: knowledge advisor phase 2 (RFC) Hive-Spec: knowledge-advisor#17054 Co-authored-by: clubanderson <407614+clubanderson@users.noreply.github.com> Signed-off-by: Karibhou <Karibhou@users.noreply.github.com>
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
|
@Karibhou this PR is back in your court ( Failing checks:
Reply here or push a new head to this branch (same sign-off); CI and the review swarm re-run automatically and the PR returns to the normal path. Queued in your relay fix queue (2 waiting): fixes are handed out before new work as soon as you have capacity. |
Open PR overlap checkBase branch: Conflicts are checked with every PR merged onto the current tip of No conflicting open PRs or same-file overlaps were found. |
|
The two red required checks are both title-shaped and fixable with an edit to the PR (no new push needed):
The PR body is currently empty apart from the hive trailer; the required checks also read it, so a short description plus the π Hive Agent: β hive: agent=scanner backend=copilot model=claude-fable-5.1 copilot=1.0.88 |
|
Correction to my earlier note: PR Type will not go green with π Hive Agent: β hive: agent=scanner backend=copilot model=claude-fable-5.1 copilot=1.0.88 |
There was a problem hiding this comment.
docs-currency β read at head 4ea6f8d; checked the RFC's codebase citations against v5. They hold (src/pkg/knowledge/primer.go:99,208, src/pkg/scheduler/kick_priming.go:256, src/pkg/config/config.go:2691, src/pkg/ioscan/daily_quota.go:47, src/crux/logscrub/pane.go:36, src/pkg/config/config.go:8762, src/crux/jsonextract/jsonextract.go:16, src/pkg/retro/retro.go:85-92, src/crux/agent/knowledge_advisor.go:41).
One stale status, low: phase 1 (#17068) merged into v5 at 19:29Z (e8347bd), after this head was pushed. The RFC still describes it as pending.
docs/rfc-17054-llm-ranked-knowledge-advisor.md:39
- **Phase 1 seam (PR #17068, merged).** `crux.KnowledgeAdviser` has two methods:
docs/rfc-17054-llm-ranked-knowledge-advisor.md:299
Each slice is independent now that phase 1 (PR #17068) has landed:
Optional: src/docs/knowledge-curator.md:687 already points at #17054 for phase 2; a link to this RFC there would make it discoverable from the operator docs.
β hive: agent=adjudicator-5 backend=copilot model=claude-fable-5.1 copilot=1.0.88
|
Hive status β updated in place; edits do not notify. Full history is in the Activity Monitor. Review findings from This PR is now carried by #17107. Both point at the same commit β Why #17107 should be the survivor: this PR's head lives on the fork Flagging for a maintainer: if you agree, this one could be closed in favour of #17107. I have not closed anything. Review findings from This appears to duplicate #17107, which carries this exact change: both PRs point at the same head commit Read both diffs: byte-identical. The content itself checks out against The red checks are the same on both heads and none is a defect in the diff:
Flagging for a maintainer: since #17107 is the branch that can be fixed and merged, this one could be closed in favour of #17107 with |
π Hive Agent:
contributor| SHA:4ea6f8deeβ hive: backend=omp model=anthropic/claude-opus-5-5 omp=omp/18.18.0