Merge pull request #68 from VibeEngineeringAI/fix/pr62-16-resolve-dataset-token-match

PR #62 follow-up 16: match resolve_dataset names on token boundaries

Author: VibeSWE

docs/tool-api.md

@@ -174,11 +174,13 @@ datasets.
   returns `not_found` if its telemetry type does not match.
 - Otherwise it scores the visible datasets that match `telemetryType` by name
   against `query`, ignoring case: 1000 if the name equals the query, 750 if the
-  query contains the name, or 500 if the name contains the query, plus 25 for
-  each query term longer than two characters that the name contains, plus 15
-  when `telemetryType` is given. It resolves only a unique top score of at least
-  500. In every other case it returns `ambiguous` with up to `limit` scored
-  `candidates`, or `not_found` if no visible dataset matches `telemetryType`.
+  query contains the name as a whole word (`-` and `_` count as part of a name,
+  so `api` is not in `rapid` or `api-gateway`), or 500 if the name contains the
+  query, plus 25 for each query term longer than two characters that the name
+  contains, plus 15 when `telemetryType` is given. It resolves only a unique top
+  score of at least 500. In every other case it returns `ambiguous` with up to
+  `limit` scored `candidates`, or `not_found` if no visible dataset matches
+  `telemetryType`.
 
 It never falls back to an arbitrary dataset.
 

src/tool_executor.rs

@@ -344,6 +344,24 @@ fn dataset_matches_telemetry_type(dataset: &Value, expected: Option<&str>) -> bo
     })
 }
 
+/// Whether `name` occurs in `query` as a whole token. Dataset names may contain
+/// `-` and `_`, so those count as part of a name rather than as boundaries.
+fn query_mentions_dataset_name(query: &str, name: &str) -> bool {
+    let is_name_character =
+        |character: char| character.is_ascii_alphanumeric() || character == '_' || character == '-';
+    !name.is_empty()
+        && query.match_indices(name).any(|(start, matched)| {
+            !query[..start]
+                .chars()
+                .next_back()
+                .is_some_and(is_name_character)
+                && !query[start + matched.len()..]
+                    .chars()
+                    .next()
+                    .is_some_and(is_name_character)
+        })
+}
+
 pub fn resolve_dataset_candidates(payload: Value, arguments: &Value) -> Value {
     let query = arguments
         .get("query")
@@ -470,7 +488,7 @@ pub fn resolve_dataset_candidates(payload: Value, arguments: &Value) -> Value {
             if !query.is_empty() && name == query {
                 score += 1_000;
                 reasons.push("exact dataset name");
-            } else if !query.is_empty() && query.contains(&name) {
+            } else if !query.is_empty() && query_mentions_dataset_name(&query, &name) {
                 score += 750;
                 reasons.push("dataset name explicitly mentioned in the question");
             } else if !query.is_empty() && name.contains(&query) {
@@ -2229,6 +2247,35 @@ mod tests {
         assert_eq!(sole_mismatch["status"], "not_found");
     }
 
+    #[actix_web::test]
+    async fn shared_dataset_resolution_requires_whole_name_mentions() {
+        let datasets = json!([{ "name": "api" }, { "name": "web" }]);
+        let embedded = resolve_dataset_candidates(
+            datasets.clone(),
+            &json!({ "query": "show rapid failures" }),
+        );
+        assert_ne!(embedded["status"], "resolved");
+
+        let mentioned =
+            resolve_dataset_candidates(datasets.clone(), &json!({ "query": "show api errors" }));
+        assert_eq!(mentioned["status"], "resolved");
+        assert_eq!(mentioned["selectedDatasets"], json!(["api"]));
+
+        let punctuated =
+            resolve_dataset_candidates(datasets, &json!({ "query": "errors in (api)?" }));
+        assert_eq!(punctuated["selectedDatasets"], json!(["api"]));
+
+        let hyphenated = json!([{ "name": "otel-metrics" }, { "name": "otel-traces" }]);
+        let longer_name = resolve_dataset_candidates(
+            hyphenated.clone(),
+            &json!({ "query": "show otel-metrics-v2 errors" }),
+        );
+        assert_ne!(longer_name["status"], "resolved");
+        let underscored =
+            resolve_dataset_candidates(hyphenated, &json!({ "query": "show my_otel-metrics" }));
+        assert_ne!(underscored["status"], "resolved");
+    }
+
     #[actix_web::test]
     async fn shared_dataset_resolution_prefers_exact_case_selection() {
         let datasets = json!([{ "name": "Logs" }, { "name": "logs" }, { "name": "Traces" }]);