open/linkedin-studio
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions

feat(linkedin-studio): RE-R3a — persist relevance score on the store record + rank the morning brief on it [skip-docs]

Browse source 
R3 slice 1 (research-deepening). Stop discarding the relevance judgment the
trend-spotter already computes: persist a 4-field TrendScore {mode, dimensions,
composite, priority} on TrendRecord (schema v2->v3, additive lossless migrate),
computed by the existing score.ts composite()+band() (one owner, no new arithmetic),
threaded item->store; then rankForBrief sorts each bucket composite-first (sentinel
-1 for unscored) and renderBrief surfaces "· <priority> (<mode>)" per body entry
(briefSummary shows the band only). First-sight only; mode-blind ranking with the mode
shown so the operator can disambiguate instruments.

- score.ts: TrendScore + requiredDimensions(mode) (ordered) + scoreEnvelope (composes
  composite+band; throws on bad dim by contract)
- types.ts: SCHEMA_VERSION 2->3; TrendRecord.score?
- store.ts: TrendInput.score?; addTrend persists first-sight (duplicate keeps it);
  migrate comment v1->v2->v3 (logic unchanged, JSON.stringify preserves the field)
- item.ts: TrendItem.score?; normalizeItem validates (non-array score/dimensions + the
  mode's five dims in [1,10]) -> structured error never throw, carries validated dims;
  itemToInput -> scoreEnvelope (no throw on the capture path; direct call throws by contract)
- brief.ts: composite-primary comparator; band+mode render; exact ranking: descriptor
- cli.ts: capture persists score via itemToInput (doc-only); add/score paths unchanged
- agents/trend-spotter.md Step 4.5: capture batch carries the Step-2 dimensions
- gate: TRENDS_TESTS_FLOOR 104->146; new unconditional Section 16j; ASSERT floor 94->99

Tests: trends 146/146 (RED two-phase: logic-RED store/brief/cli; stub-first then
assertion-RED score/item). Gate green (Passed 114 / Failed 0; 113 checks >= 99).
Hook suite 139/139 untouched. Counts 27/19/29 unchanged. No new source file/agent/command.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VmHCQjJHUyWwxGAVVjNLgp
This commit is contained in:
Kjell Tore Guttormsen 2026-06-24 14:05:27 +02:00
commit e169c78710
14 changed files with 829 additions and 40 deletions
Download patch file Download diff file Expand all files Collapse all files

5
scripts/trends/src/cli.ts
View file

@ -14,7 +14,10 @@
*
* The capture agent (research-engine) folds freshly-polled trends into the store via
* `capture` (the normalizing batch path: stdin → normalizeItem(s) → itemToInput →
* addTrend), and reasons over accumulated history via `query`/`list`. `brief` (RE-R2b)
* addTrend) — which, when an item carries the agent's five judgment scores (RE-R3a),
* persists an optional relevance `score` (the deterministically-computed composite + band,
* one owner) first-sight on the record so the morning brief ranks on it — and reasons over
* accumulated history via `query`/`list`. `brief` (RE-R2b)
* renders a dated, pillar-ranked morning brief over the store to a Markdown file the
* SessionStart hook surfaces. `add` is the MANUAL single-trend path (raw flags, no
* normalization, publish-date-free). The polling + relevance-scoring itself lives