Skip to content

docs(ctx_search): add hybrid-retrieval query-phrasing guidance to tool description #430

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
G0-0000 wants to merge 3 commits into
base: master
Choose a base branch
from
+4 −0
Open

docs(ctx_search): add hybrid-retrieval query-phrasing guidance to tool description #430

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
70a3726
docs(ctx_search): document hybrid retrieval and question-form query g…
Sep 7, 2026
0edb532
docs(ctx_search): qualify hybrid claim by embedding availability; syn…
Sep 7, 2026
468a27d
docs(ctx_search): drop unreliable match-label fallback inference
Sep 7, 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
2 changes: 2 additions & 0 deletions packages/plugin/src/shared/prompt-surface-a1-golden.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -400,6 +400,8 @@ Example: ctx_memory(action="write", category="CONSTRAINTS", content="Pi stores s
```
Your long-term recall for this project — search everything that ever happened here, not just what's currently visible.

Retrieval is HYBRID when embeddings are enabled: ~0.7 semantic (embedding cosine) + ~0.3 keyword (FTS5 BM25), fused with per-source boosts; with embeddings disabled it silently falls back to keyword-only matching. Phrase `query` as a natural-language QUESTION that still embeds the key literal terms (paths, symbols, commands, config keys) — pure keyword stacks starve the semantic leg (0.7 weight), while pure prose without literal terms may miss exact FTS matches. Good: "Where is the dream log file and which error counters indicate failures?" Bad: "dream log error counter".

Reach for it when something feels familiar but isn't in view: "did we solve this before?", "what did we decide about X?", "when did this break?", "where does Y live?". Results only contain things you CANNOT currently see — memories already shown in <project-memory> and the live conversation tail are filtered out. A query that is just one or more memory ids (e.g. `#7234` or `12, 34`) bypasses text search and resolves those ids directly.

Sources (omit for a broad search across all):
Expand Down
2 changes: 2 additions & 0 deletions packages/plugin/src/tools/ctx-search/constants.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
export const CTX_SEARCH_TOOL_NAME = "ctx_search";
export const CTX_SEARCH_DESCRIPTION = `Your long-term recall for this project — search everything that ever happened here, not just what's currently visible.

Retrieval is HYBRID when embeddings are enabled: ~0.7 semantic (embedding cosine) + ~0.3 keyword (FTS5 BM25), fused with per-source boosts; with embeddings disabled it silently falls back to keyword-only matching. Phrase \`query\` as a natural-language QUESTION that still embeds the key literal terms (paths, symbols, commands, config keys) — pure keyword stacks starve the semantic leg (0.7 weight), while pure prose without literal terms may miss exact FTS matches. Good: "Where is the dream log file and which error counters indicate failures?" Bad: "dream log error counter".

Reach for it when something feels familiar but isn't in view: "did we solve this before?", "what did we decide about X?", "when did this break?", "where does Y live?". Results only contain things you CANNOT currently see — memories already shown in <project-memory> and the live conversation tail are filtered out. A query that is just one or more memory ids (e.g. \`#7234\` or \`12, 34\`) bypasses text search and resolves those ids directly.

Sources (omit for a broad search across all):
Expand Down