fix(read): fixed column truncation mutating snapshot with display content
- Column truncation is now applied to a cloned array so `collectedLines` retains on-disk content for snapshot recording. - Snapshots bound to hashline TAGs now hold the original file text, preventing hash-mismatch failures on subsequent edits to files with long lines. - Added regression tests covering full-file, range, multi-range reads and a live edit-after-read scenario.
This commit is contained in:
@@ -17,8 +17,9 @@
|
||||
* `BlobStore` keep writing to `~/.omp/agent/...`. Reach for object storage
|
||||
* if you need those off-host too.
|
||||
*/
|
||||
import { SQL } from "bun";
|
||||
|
||||
import { createAgentSession, SessionManager, SqlSessionStorage } from "@oh-my-pi/pi-coding-agent";
|
||||
import { SQL } from "bun";
|
||||
|
||||
// Pick one — Bun.SQL auto-detects the dialect from the URL scheme.
|
||||
//
|
||||
|
||||
Reference in New Issue
Block a user