perf(hints): optimized profile disables per-result hints by default - #113
Merged
Conversation
The optimized profile is the token-minimizing default — it already implies thin schemas. But per-result _hints/_suggestion blocks (~30-50 tokens each) stayed on, and a usage audit found they convert poorly (the ts_execute nudge fired hundreds of times without moving adoption). So optimized now disables them too; the tokens were a measured overhead there. Explicit TS_NO_HINTS=0/1 still wins on any profile. Non-optimized profiles unchanged.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
First of the measured token-overhead removals. A 3-day usage audit (6,785 real calls) showed the per-result hint/suggestion blocks (~30-50 tokens each) fire on most nav results but convert poorly — the ts_execute nudge fired 228 times while adoption stayed 310 vs 4,502 nav calls. On the
optimizedprofile (the recommended token-minimizing default, which already thins schemas) they were still on.optimizednow disables hints by default, mirroring the thin-schema logic.TS_NO_HINTS=0opts back in on any profile;=1still forces off; non-optimized profiles are unchanged, so existing hint tests pass untouched.Remaining (bigger, not rushed): server-side dedup so
get_full_contextomits source already served this session (the measuredread→get_full_context×295 waste) — needs careful source-matching between code paths, worth its own pass.