mirror of
https://github.com/vitorpamplona/amethyst.git
synced 2026-10-06 03:38:23 +00:00
Claude
65c683c9c7
`classifyRowError` read SQLite's exception text to decide whether a row that failed to insert was a duplicate, a superseded replaceable, or a genuine write failure. That text is the driver's business, not a contract: the bundled JVM driver spells out `UNIQUE constraint failed: event_headers.id`, while Android's wraps the same failure in an `android.database.SQLException` whose message is **null**. So on the Android host every duplicate fell through to `Failed`, which the relay renders as `OK false "error: SQLException"` — an answer clients retry forever, and a direct violation of STORE-W01/W02 (`OK true` with the `duplicate:` prefix). Four commonTest suites caught it and failed on that target only: NostrServerTest x3 and LiveNegentropyIndexStoreTest. The classifier now asks the connection instead. It already runs after the savepoint rollback, so the connection shows pre-insert state and the two questions have exact answers: is this id already stored, and does a stored version already beat this one at its replaceable/addressable coordinate? The latter is the exact complement of `displacedBy`'s predicate, so a disk error while inserting a *winning* version still reports `Failed` rather than turning into a silent `OK true`. Trigger RAISEs (`blocked:`, `not allowed`) keep being decided by text — they leave no database-visible trace. One behaviour change, noted in the skill's changelog: re-offering a stored replaceable/addressable event byte-for-byte now reports DUPLICATE where the JVM driver previously reported SUPERSEDED. It violates both indexes and which one SQLite names first is up to the driver; the id answer is the one that holds everywhere (and is the truer sentence). Both carry the `duplicate:` prefix, so the wire answer is unchanged. `InsertOutcomeClassificationTest` pins all of this at the store level on both targets, including the guard that a winning version at an occupied coordinate is still Accepted. Also corrects a false claim in the previous commit's message: moving the cordn and contextvm tests to `jvmAndroidTest` did NOT make them run on the Android host. `androidHostTest` has no `dependsOn(jvmAndroidTest)` — only `jvmTest` does — so those suites run on the JVM target alone. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012BfD4txdnsaPRXmNXbup9n