Design: where should semantic context evaluation live?
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 25/100
Research direction
Read the existing reference/context-agent and the closed PR #10 for prior design context. Compare the three proposed homes against the listed deciding factors; the issue is done when a decision is recorded before implementation begins.
Written by the indexing model from the issue text.
Description
The current reference/context-agent is scoped to property-registry lookup + bitmap-based property targeting. Six semantic evaluation concerns are unbuilt on main:
- EmbeddingMatch — cosine similarity between query embedding and content embedding
- KeywordMatch — set intersection of required/blocked keywords
- BrandSafety — category blocklist
- GeoFilter — allow/block lists
- DaypartFilter — day-of-week + hour ranges
- CatalogMatch — product catalog to content topics
Prior design lived in closed PR #10. Before rebuilding, decide the home.
Options
- (A) Expand
context-agentto carry a pluggable evaluator registry alongside the property registry - (B) New
reference/semantic-agentas a separate reference service - (C) Move these into
targeting/as configurable predicates
Deciding factors
- Whether context-agent stays a lightweight registry lookup or grows into an evaluator
- Whether semantic matching is latency-critical (argues for colocating with targeting)
- Whether these need to be independently versioned and deployed
Decision needed before any implementation. Suggested owner: @bokelley.
- Dominant language
- Go
- Stars
- 4
- Forks
- 2
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 25
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from adcontextprotocol/adcp-go
-
CreativeInput carries no revision_id or localization (follow-up to #545)Possibly taken @sujanchalla0510 claimed this 19 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
adcontextprotocol/adcp-go#567 ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 25/100
adcontextprotocol/adcp-go#600 ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 38/100
adcontextprotocol/adcp-go#597 ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 30/100
adcontextprotocol/adcp-go#588 · 3 comments ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 25/100
adcontextprotocol/adcp-go#579 ·
Maintainers usually reply within 1 day
All issues in adcontextprotocol/adcp-go
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 77/100
JakeChampion/lang#14392 ·
Maintainers usually reply within 1 day
-
agent-butler-finding bug
Difficulty 1/5 1-3 hours Newbie friendliness 84/100
jordansmall/spindrift#6557 ·
Maintainers usually reply within 1 day
-
[Bug] Custom tool truncation leaves unused stream copies openPossibly taken @OUAO-FRANK claimed this today. Open
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
[v3] KeyBindingManager calls (Add/Remove) are not converted into a case-insensitive accelerator.KeyOpenBug
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 1 day
-
enhancement
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
crmne/hyprmoncfg#114 · 1 comment ·
Maintainers usually reply within 1 day