mirror of
https://github.com/qdrant/qdrant.git
synced 2026-09-26 07:57:37 -05:00
Andrey VasnetsovandClaude Opus 5
81e9fb3e75
* [UpdateOnly] Honor upsert update_mode in the batch writer The writer rejected every `UpsertPointsConditional`. Accept the ones whose condition is empty — `insert_only` and `update_only` — since existence is the whole gate they need, and locating a batch's points already answers it. The gate is evaluated per mutation at its position in the fold, so an `insert_only` upsert sees a point an earlier operation of the same batch created, matching a leader that resolves each operation only after the ones before it were applied. A conditional upsert may therefore not discard the mutations it follows. Rejecting an upsert also means never reading the point it would have overwritten: `needs_stored_point` asks whether the first mutation that applies to an existing point discards it, so an `insert_only` batch pays nothing for the ids that are already taken. A conditional upsert carrying a real filter is still rejected — evaluating one needs payload indexes the writer never fetches. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * [UpdateOnly] State contracts in the update-mode docstrings Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * [UpdateOnly] Trim the update-mode diff Drop `--update-mode` from edge-shard-update: the modes are covered by unit and end-to-end tests, and the flag cost a wrapper enum, a conversion and a parameter threaded through both run paths. The tool still reports rejected points, which the exhaustive match requires. Inline `always_applies` into its one caller, drop the two test-batch wrappers over `conditional_batch`, drop the `update_only` fold test whose truth table two other tests already assert, and shorten two over-long comment blocks. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>