docs: document semantic_cache_max_candidates recall tradeoff#2071
Merged
docs: document semantic_cache_max_candidates recall tradeoff#2071
Conversation
github-actions
bot
added
documentation
Add comprehensive documentation explaining the recall vs performance tradeoff of the semantic_cache_max_candidates parameter (controls SQL LIMIT in ResponseCache::get_semantic() lookup): - Config help: expanded doc comments in providers.rs with tuning guidance (50+ for recall-focused, 5 for performance-focused, default 10 balanced) - Debug logs: full lifecycle logs covering lookup start, per-candidate cosine similarity scores, scan summary, and hit/miss verdicts - Explains SQL LIMIT clause and how it affects cache hit probability - Documents env override: ZEPH_LLM_SEMANTIC_CACHE_MAX_CANDIDATES - Also expanded semantic_cache_threshold doc comments for completeness Fixes #2031
bug-ops
force-pushed
the
feat-2031-semantic-cache-docs
branch
from
1ab2ee6 to
f11245c
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Documents the semantic_cache_max_candidates parameter and its recall vs performance tradeoff in PR #2029. Users can now understand why setting
max_candidates=10limits the number of cached entries examined during similarity lookup.Changes
Config help comments (
crates/zeph-config/src/providers.rs):semantic_cache_thresholddocumentationDebug logs (
crates/zeph-core/src/agent/tool_execution/mod.rs):Per-candidate debug logs (
crates/zeph-memory/src/response_cache.rs):CHANGELOG updated
Validation
cargo +nightly fmt --checkcargo clippy --workspace -- -D warningscargo nextest run --workspace --lib --bins(5734 tests)Fixes #2031