feat(agent-service): add stateless /recommend endpoint (V1 hardcoded)#6436
Open
gupta-sahil01 wants to merge 1 commit into
Open
feat(agent-service): add stateless /recommend endpoint (V1 hardcoded)#6436gupta-sahil01 wants to merge 1 commit into
gupta-sahil01 wants to merge 1 commit into
Conversation
Ambient operator recommender, Version 1 (apache#5240). Adds a stateless POST /api/recommend that, given the operator a user just added, returns a short ranked list of likely next operators for the canvas to render as ghost suggestions. V1 ranks from a hardcoded rule table (no LLM call, no persistent state), so it ships and validates the full pipeline at zero API cost, per the discussion's V1/V2 split. Suggestions are validated against the live operator catalog (WorkflowSystemMetadata) when available, so a stale rule degrades to "not suggested" rather than a broken ghost. The response carries a `strategy` discriminator ("hardcoded") so V2 can swap in a small LLM behind the same request/response shape without a breaking change.
Contributor
Automated Reviewer SuggestionsBased on the
|
Contributor
|
👋 Thanks for your first contribution to Texera, @gupta-sahil01! If you're looking for a good place to start, browse issues labeled You can drive common housekeeping yourself by commenting one of these commands on its own line:
Each command must match exactly: |
Contributor
|
Really clean V1 — the hardcoded/strategy-discriminator split and the catalog validation are a nice way to ship the whole pipeline at zero API cost. Two forward-looking notes, both about what the endpoint
Neither blocks V1 — just wanted to surface them while the request shape is still easy to evolve. |
Comment on lines
+412
to
+418
| .post("/", ({ body }) => recommendOperators(body as RecommendationRequest, WorkflowSystemMetadata.getInstance()), { | ||
| body: t.Object({ | ||
| operatorType: t.String({ minLength: 1 }), | ||
| existingOperatorTypes: t.Optional(t.Array(t.String())), | ||
| limit: t.Optional(t.Number()), | ||
| }), | ||
| }); |
Comment on lines
+65
to
+69
| test("rejects an empty operatorType as 400", async () => { | ||
| const res = await postRecommend({ operatorType: "" }); | ||
| expect(res.status).toBe(400); | ||
| }); | ||
|
|
Comment on lines
+409
to
+410
| set.status = 500; | ||
| return { error: errorMessage || "Internal server error" }; |
Comment on lines
+67
to
+68
| /** Recommended operator type; always a real, catalog-known type. */ | ||
| operatorType: string; |
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #6436 +/- ##
============================================
+ Coverage 70.17% 70.28% +0.10%
Complexity 3387 3387
============================================
Files 1142 1145 +3
Lines 44844 45017 +173
Branches 4949 4949
============================================
+ Hits 31468 31638 +170
- Misses 11739 11742 +3
Partials 1637 1637
*This pull request uses carry forward flags. Click here to find out more. ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
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.
Ambient operator recommender, Version 1 (#5240). Adds a stateless POST /api/recommend that, given the operator a user just added, returns a short ranked list of likely next operators for the canvas to render as ghost suggestions.
V1 ranks from a hardcoded rule table (no LLM call, no persistent state), so it ships and validates the full pipeline at zero API cost, per the discussion's V1/V2 split. Suggestions are validated against the live operator catalog (WorkflowSystemMetadata) when available, so a stale rule degrades to "not suggested" rather than a broken ghost. The response carries a
strategydiscriminator ("hardcoded") so V2 can swap in a small LLM behind the same request/response shape without a breaking change.What changes were proposed in this PR?
Backend half (PR 1 of 2) of the ambient operator recommender, Version 1 — see #6293 (design discussion #5240).
Adds a stateless
POST /api/recommendendpoint toagent-service: given the operator a user just added to the canvas, it returns a short ranked list of likely next operators for the frontend to render as ghost suggestions.WorkflowSystemMetadata) when available, so a stale rule degrades to "not suggested" rather than a broken suggestion.strategydiscriminator ("hardcoded"/"llm") so V2 can swap in a small-LLM ranker behind the same request/response shape without a breaking change.The frontend that consumes this endpoint (ghost rendering, opt-in flag, click-to-materialize) follows in PR 2.
Any related issues, documentation, discussions?
How was this PR tested?
bun testinagent-service/— 131 passed, including newsrc/recommender/recommender.spec.tsandsrc/server.recommend.spec.tscovering ranking order, catalog validation, terminal sinks (no suggestions), limit clamping, and 400s on malformed/empty input. Also verified live:POST /api/recommendwith{"operatorType":"CSVFileScan"}returns the expected ranked JSON.Was this PR authored or co-authored using generative AI tooling?
Generated-by: Anthropic Claude (Claude Code)