insights: push sms search filters server-side, render snippets, expand fts5 docs

- Refactor search_messages_with_contact -> search_messages(query, &SmsSearchParams)
  exposing date_from / date_to / offset / is_mms / has_media; drop the over-fetch
  + client-side date post-filter that could silently drop in-window hits past
  position 100.
- Surface SMS-API's <mark>-wrapped snippet for MMS messages that only matched
  via message_parts_fts (attachment text / filename) - pre-snippet, those
  rendered as a blank body preview to the LLM.
- Expose is_mms / has_media on the search_messages tool schema; expand the
  FTS5 syntax docs with worked examples for phrase / prefix / boolean / NEAR
  / grouping so the model picks the right operator.
- Unit tests for format_search_hits (body fallback, snippet preferred, MMS
  attachment-only regression, empty-snippet fallback) and strip_mark_tags.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Cameron Cordes
2026-05-11 19:20:19 -04:00
parent 6620fa48d7
commit 7329cc5ce7
2 changed files with 218 additions and 89 deletions
+49 -10
View File
@@ -257,30 +257,45 @@ impl SmsApiClient {
}
/// Search message bodies via the Django side's FTS5 / semantic / hybrid
/// endpoint. `mode` selects the ranking strategy:
/// endpoint. `params.mode` selects the ranking strategy:
/// - "fts5" keyword-only, supports phrase / prefix / boolean / NEAR
/// - "semantic" embedding similarity
/// - "hybrid" both merged via reciprocal rank fusion (recommended)
///
/// The SMS-API endpoint accepts `contact_id` natively; date filtering is
/// the caller's responsibility (post-filter on the returned rows).
pub async fn search_messages_with_contact(
/// All of `contact_id`, `date_from` / `date_to` (unix seconds), `is_mms`,
/// `has_media`, and `offset` are pushed to SMS-API server-side so the
/// filtered+paginated result set is exact rather than a client-side
/// over-fetch.
pub async fn search_messages(
&self,
query: &str,
mode: &str,
limit: usize,
contact_id: Option<i64>,
params: &SmsSearchParams<'_>,
) -> Result<Vec<SmsSearchHit>> {
let mut url = format!(
"{}/api/messages/search/?q={}&mode={}&limit={}",
self.base_url,
urlencoding::encode(query),
urlencoding::encode(mode),
limit
urlencoding::encode(params.mode),
params.limit,
);
if let Some(cid) = contact_id {
if let Some(cid) = params.contact_id {
url.push_str(&format!("&contact_id={}", cid));
}
if let Some(off) = params.offset {
url.push_str(&format!("&offset={}", off));
}
if let Some(from) = params.date_from {
url.push_str(&format!("&date_from={}", from));
}
if let Some(to) = params.date_to {
url.push_str(&format!("&date_to={}", to));
}
if let Some(is_mms) = params.is_mms {
url.push_str(&format!("&is_mms={}", is_mms));
}
if let Some(has_media) = params.has_media {
url.push_str(&format!("&has_media={}", has_media));
}
let mut request = self.client.get(&url);
if let Some(token) = &self.token {
@@ -383,6 +398,30 @@ pub struct SmsSearchHit {
/// Present for semantic / hybrid modes; absent for fts5.
#[serde(default)]
pub similarity_score: Option<f32>,
/// SMS-API-generated excerpt around the match, wrapped in `<mark>` tags.
/// For MMS messages that only matched via attachment text / filename
/// (empty `body`), the snippet is the only meaningful preview.
#[serde(default)]
pub snippet: Option<String>,
}
/// Optional filter / paging knobs for [`SmsApiClient::search_messages`].
/// All fields except `mode` and `limit` map 1:1 to the same-named SMS-API
/// query params (added in the 2026-05 search-enhancements release).
#[derive(Debug, Clone)]
pub struct SmsSearchParams<'a> {
pub mode: &'a str,
pub limit: usize,
pub contact_id: Option<i64>,
/// Unix-seconds inclusive lower bound on `date`.
pub date_from: Option<i64>,
/// Unix-seconds inclusive upper bound on `date`.
pub date_to: Option<i64>,
/// `Some(true)` = MMS only, `Some(false)` = SMS only, `None` = both.
pub is_mms: Option<bool>,
/// `Some(true)` = only messages with image/video/audio attachments.
pub has_media: Option<bool>,
pub offset: Option<usize>,
}
#[derive(Deserialize)]