luxin-cli 0.2.8 → 0.2.9

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -6,6 +6,46 @@ provenance; this file is the human- and agent-readable release map.
6
6
 
7
7
  ## Unreleased
8
8
 
9
+ ## 0.2.9 - 2026-08-17
10
+
11
+ Discovery, batch work, and recovery — the release for agents doing real
12
+ multi-image jobs.
13
+
14
+ - New command: `luxin models overview` — a ~2KB orientation payload with
15
+ category groups and counts, the cheapest executable model per category,
16
+ alias hints, and runnable next commands. Read this instead of the full list.
17
+ - New command: `luxin models find` — terse, cost-sorted decision rows with
18
+ `--max-credits`, `--limit` (default 10), `--sort credits|usd`, a free-text
19
+ query, and the existing filters. Rows carry aspect-ratio support and honest
20
+ availability, include cataloged-but-not-yet-wired models (clearly marked,
21
+ ranked last), and report `total_matched` with a narrowing hint. The query
22
+ that used to return 4,000+ lines now answers in ~130. (#2114)
23
+ - `models list` gains the same `--limit` / `--sort` / `--max-credits` flags
24
+ and is byte-identical when you don't use them. Against an older hosted API,
25
+ find/overview/narrowing degrade honestly client-side and say so in
26
+ `warnings`.
27
+ - New: `luxin create --batch items.json` (or `--batch -`) — sequential
28
+ multi-image work as one command: shared defaults plus per-item prompts,
29
+ whole-document validation before any spend. `--dry-run` prices the whole
30
+ job with the same debit math the live run charges, checks your credits AND
31
+ the daily job cap, and answers "your credits cover K of N; the batch stops
32
+ at item K+1" with the top-up sized to the actual need. At any wall the
33
+ completed items are delivered and the batch stops cleanly with one digest
34
+ and one recovery block; re-running with the same `--batch-id` skips
35
+ completed, unchanged items. `seed_policy: fixed | increment | random` where
36
+ the model supports a seed. (#2304)
37
+ - Recovery handle in the envelope: live create/edit responses now carry
38
+ `data.idempotency_key` on success and `error.recovery.idempotency_key` plus
39
+ a re-runnable `error.recovery.recover_command` on failure, so an
40
+ interrupted spend is recoverable from the envelope alone. stdout is exactly
41
+ one JSON document per invocation — now stated plainly in the contract; the
42
+ in-flight recovery line stays on stderr. (#2240)
43
+ - Hosted-side, already live and noted for completeness: create/edit responses
44
+ echo `effective_parameters` (each knob tagged explicit / default_policy /
45
+ provider_default) so you can see the configuration that actually ran, and
46
+ `resolution` without `quality` on xai.grok-imagine-image-2.0 now sends the
47
+ medium tier you were already being quoted. (#2310)
48
+
9
49
  ## 0.2.8 - 2026-08-12
10
50
 
11
51
  - New command: `luxin skill` prints the full usage guidance from bundled