Conversation
WIP note plus local enqueue/score helpers. No product behavior change. Co-authored-by: aria <aria@engramhq.com>
6 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Temporary commit of a reviewer handoff for the in-flight n=1540 product
/recallmeasurement on SHAbbe55f7(PR #184 already onmain/dev). No product behavior change.The working tree on
bbe55f7was otherwise clean (n=1540 work was in/tmpand the live DB). This PR persists the handoff note plus local enqueue/score helpers so a planner can resume without reconstructing the pitfalls.Changes
docs/research/handover-n1540-agent-2026-09-11.md— operational truth: landed SHAs, P84/11.4% pins, live tenantlocomo-n1540-bbe55f7, harness bugs (staging recall URL, FIFO extract, 8h search-settle), kill list, what the next plan must contain.evals/tools/n1540_preingest.py— enqueue all 10 LoCoMo convs withwait_jobs=Falseso extract can run per-subject in parallel.evals/tools/n1540_run_product_recall.sh— skip-ingest product/recallscorer; refuses a non-local product-recall base URL.Test plan
gofmt -l .N/A (no Go).go vet ./.../go test ./...not required for this docs PR.:18200, 10 workers); score with the helper afterextraction_jobspending+in_progress hit 0.Linear / tracking
Follow-on to PR #184 merge /
mainFF. No new Linear id.Risk / follow-ups
/recallstays 11.4% until n=1540 JSON lands./tmp/brainy_n1540.env(injected keys).