You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: CHANGELOG.md
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -7,6 +7,7 @@
7
7
-**Index versioning (Phase 06)**: Index artifacts are versioned via `index-meta.json`. Mixed-version indexes are never served; version mismatches or corruption trigger automatic rebuild.
8
8
-**Crash-safe rebuilds (Phase 06)**: Full rebuilds write to `.staging/` and swap atomically only on success. Failed rebuilds don't corrupt the active index.
9
9
-**Relationship sidecar (Phase 07)**: New `relationships.json` artifact containing file import graph, reverse imports, and symbol export index. Updated incrementally alongside the main index.
10
+
-**References confidence + hints (Phase 08)**: `get_symbol_references` now includes `confidence: "syntactic"` and `isComplete: boolean` to help agents assess result completeness. `search_codebase` results now include a structured `hints` object (capped callers/consumers/tests ranked by frequency) drawn from the relationships sidecar. `get_component_usage` removed from MCP surface (11→10 tools).
10
11
- Tree-sitter-backed symbol extraction is now used by the Generic analyzer when available (with safe fallbacks).
-**Pattern signals** per result: `trend` (Rising/Declining — Stable is omitted) and `patternWarning` when using legacy code
122
-
-**Relationships** per result: `importedByCount` and `hasTests` (condensed)
122
+
-**Relationships** per result: `importedByCount` and `hasTests` (condensed) + **hints** (capped ranked callers, consumers, tests)
123
123
-**Related memories**: up to 3 team decisions, gotchas, and failures matched to the query
124
124
-**Search quality**: `ok` or `low_confidence` with confidence score and `hint` when low
125
125
-**Preflight**: `ready` (boolean) + `reason` when evidence is thin. Pass `intent="edit"` to get the full preflight card. If search quality is low, `ready` is always `false`.
@@ -137,7 +137,11 @@ Snippets are opt-in (`includeSnippets: true`). Default output is lean — if the
6.**Contamination control** — test file filtering for non-test queries.
40
39
7.**File deduplication** — best chunk per file.
41
40
8.**Stage-2 reranking** — cross-encoder (`Xenova/ms-marco-MiniLM-L-6-v2`) triggers when the score between the top files are very close. CPU-only, top-10 bounded.
42
-
9.**Result enrichment** — compact type (`componentType:layer`), pattern momentum (`trend` Rising/Declining only, Stable omitted), `patternWarning`, condensed relationships (`importedByCount`/`hasTests`), related memories (capped to 3), search quality assessment with `hint` when low confidence.
41
+
9.**Result enrichment** — compact type (`componentType:layer`), pattern momentum (`trend` Rising/Declining only, Stable omitted), `patternWarning`, condensed relationships (`importedByCount`/`hasTests`), structured hints (capped callers/consumers/tests ranked by frequency), related memories (capped to 3), search quality assessment with `hint` when low confidence.
0 commit comments