insight-chat: include Date taken + GPS in bootstrap photo context

The bootstrap system message gave the model a file path and (in
hybrid mode) a visual description, but no temporal anchor. Models
defaulted to today's date when calling get_sms_messages — Nov 2014
photos were getting "2024-03-11" passed as `date`, missing every
historical message and leading the model to confidently misreport
context.

This commit folds two more EXIF-sourced facts into the
--- PHOTO CONTEXT --- block:

  Date taken: <YYYY-MM-DD or "unknown">
  GPS: <lat, lon to 4dp>           (omitted when no GPS)

Resolution waterfall for date_taken matches the documented canonical
date pipeline at the EXIF / filename steps, but intentionally stops
short of the fs-time fallback `generate_agentic_insight_for_photo`
uses — for chat we'd rather show "unknown" than mislead the model
with an inode mtime. GPS is taken straight from EXIF when both
lat/lon are populated; absent GPS suppresses the line entirely so
the model doesn't hallucinate coordinates.

InsightGenerator gains a `fetch_exif(file_path)` accessor (crate-
visible) so the chat service doesn't need its own ExifDao plumbing.

build_bootstrap_system_message picks up two new params (date,
gps); existing tests updated and 5 new tests cover:
- date present / absent / waterfall (EXIF wins, filename fallback,
  None when neither source has it)
- GPS present / absent
- ordering (path → date → visual)

Total insight_chat unit tests: 33 (up from 27).
This commit is contained in:
Cameron Cordes
2026-05-08 11:14:39 -04:00
parent a0ec1a5080
commit 3699e059a2
2 changed files with 166 additions and 16 deletions

View File

@@ -229,6 +229,17 @@ impl InsightGenerator {
None
}
/// Look up the EXIF row for a photo. Returns `None` when no row
/// exists yet (file watcher hasn't reached it) or the DAO call
/// fails. Used by callers — including the chat-bootstrap path —
/// that need a few specific fields (date_taken, GPS) without
/// duplicating DAO plumbing.
pub(crate) fn fetch_exif(&self, file_path: &str) -> Option<crate::database::models::ImageExif> {
let cx = opentelemetry::Context::current();
let mut dao = self.exif_dao.lock().expect("Unable to lock ExifDao");
dao.get_exif(&cx, file_path).ok().flatten()
}
/// Load image file, resize it, and encode as base64 for vision models
/// Resizes to max 1024px on longest edge to reduce context usage
pub(crate) fn load_image_as_base64(&self, file_path: &str) -> Result<String> {