Skip to content

docs: show recall() scoringWeights on SKILL.md (WALM-616) #899

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
HoangDucBach wants to merge 2 commits into
base: dev
Choose a base branch
from
Open

docs: show recall() scoringWeights on SKILL.md (WALM-616) #899

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
79cd6fc
docs: show recall() scoringWeights on SKILL.md (WALM-616)
HoangDucBach Sep 11, 2026
89e29ac
docs: define ScoringWeights on SKILL.md (WALM-616)
HoangDucBach Sep 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 11 additions & 1 deletion SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,7 +152,7 @@ const stored = await memwal.waitForRememberJob(accepted.job_id, {
|---|---|---|
| `remember(text, namespace?)` | Accept one memory job immediately | `{ job_id, status }` |
| `rememberAndWait(text, namespace?, opts?)` | Store one memory and wait for completion | `{ id, job_id, blob_id, owner, namespace }` |
| `recall({ query, limit?, topK?, namespace?, maxDistance? })` *(preferred)* or `recall(query, limit?, namespace?)` | Semantic search for memories | `{ results: [{ blob_id, text, distance }], total }` |
| `recall({ query, limit?, topK?, namespace?, maxDistance?, sort?, scoringWeights? })` *(preferred)* or `recall(query, limit?, namespace?)` | Semantic search for memories | `{ results: [{ blob_id, text, distance }], total }` |
| `analyze(text, namespace?)` | Extract facts and accept one memory job per fact | `{ job_ids, facts, fact_count, status, owner }` |
| `analyzeAndWait(text, namespace?, opts?)` | Extract facts and wait for all fact jobs to complete | `{ results, facts, total, succeeded, failed, owner }` |
| `restore(namespace, limit?)` | Rebuild missing index entries from Walrus | `{ restored, skipped, failed, total, namespace, owner, truncated }` |
Expand Down Expand Up @@ -208,9 +208,19 @@ interface RecallOptions {
topK?: number; // alias of limit; if both are set, topK wins
namespace?: string;
maxDistance?: number;
sort?: "relevance" | "recent";
scoringWeights?: ScoringWeights; // sent as scoring_weights; omit to keep cosine order

@ducnmm ducnmm Sep 11, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[suggestion] scoringWeights?: ScoringWeights is the advertised contract this ticket is closing, but ScoringWeights is never defined in SKILL.md. Agents reading only this file still cannot see { semantic?, recency?, recencyHalfLifeDays?, importance? }.

Suggestion: Add the ScoringWeights interface next to RecallOptions (same fields as packages/sdk/src/types.ts). A one-liner that sort: "recent" is newest-wins (over-fetch then write-time) and scoringWeights only re-ranks the cosine window would match the SDK docs.

@HoangDucBach HoangDucBach Sep 11, 2026

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added ScoringWeights next to RecallOptions, plus the sort vs weights one-liner.

}

interface ScoringWeights {
semantic?: number; // default 1
recency?: number; // default 0
recencyHalfLifeDays?: number; // default 30
importance?: number; // default 0
}

// `topK` and `limit` are aliases for the same value; if both are provided, `topK` takes precedence.
// `sort: "recent"` is newest-wins (over-fetch then write-time). `scoringWeights` only re-ranks the cosine window.

interface RememberBulkAcceptedResult {
job_ids: string[];
Expand Down
Loading