chore(release): prepare 0.7.9

CHANGELOG.md

@@ -2,16 +2,18 @@
 
 ## Unreleased
 
-- Refresh the static capability snapshot to `command-code@1.87.2`, which removes image, reasoning, and effort metadata for the retired free MiniMax M3.1 Flash and Ornith 1.5 122B variants. Paid variants and pricing are unchanged.
+## 0.7.9 - 2026-10-22
 
-- Refresh the static capability snapshot to `command-code@1.87.1`, which publishes no model metadata changes, and re-verify display pricing on 2026-10-22 for all 94 advertised models. Both free promotions ended on 2026-10-22 and the API dropped the models, so remove the `minimax/minimax-m3.1-flash:free` and `ornith/ornith-1.5-122b:free` display prices, their temporary-pricing guards, and their fixture entries; `TEMPORARY_PRICING` is empty until the pricing page publishes another dated promotion. Paid MiniMax M3.1 Flash ($0.15 input / $0.60 output / $0.015 cache read) and paid Ornith 1.5 122B ($0.16 input / $0.64 output / $0.02 cache read) rates are unchanged, and Beam's capacity-limited free pricing still has no published expiry.
+- Pin the capability snapshot to `command-code@1.87.2`, covering all 94 advertised models; the `x-command-code-version` header sent on the generate fallback reports that CLI version.
+- Add reviewed display pricing for the newly advertised models, verified against the official pricing page on 2026-10-22: `minimax/minimax-m3.1-flash` at $0.15 input / $0.60 output / $0.015 cache read per million tokens, with image input, reasoning and `low`/`medium`/`high`/`xhigh`/`max` efforts; `ornith/ornith-1.5-122b` at $0.16 input / $0.64 output / $0.02 cache read with image input and reasoning but no selectable efforts; and the capacity-limited free `reflection/beam:free`, which gains reasoning with the same five efforts and a 131,072-token output limit. No cache-write charge applies to the new models.
+- Add image input, reasoning, and selectable `low`/`medium`/`high` efforts for `meta/muse-spark-open` and `nvidia/nemotron-3.5-super-vl` ([#167](https://github.com/patlux/pi-commandcode-provider/pull/167)).
+- Retire models the API no longer advertises: the free `stealth/cat-jam:free` preview, `inclusionai/ling-3.0-flash-sante:free`, and the two promotions that ended on 2026-10-22 — `minimax/minimax-m3.1-flash:free` (10:45 UTC) and `ornith/ornith-1.5-122b:free` (06:00 UTC). Their capability metadata, display prices, dated pricing guards and fixture entries are removed, so `TEMPORARY_PRICING` is empty until the pricing page publishes another dated promotion. The paid variants keep their rates, and Beam's capacity-limited free pricing has no published expiry ([#169](https://github.com/patlux/pi-commandcode-provider/pull/169)).
+- Disable npm lifecycle scripts while the catalog checker inspects the published CLI package, so an upstream `preinstall` or `postinstall` script cannot run during model-metadata comparison or synchronization ([#157](https://github.com/patlux/pi-commandcode-provider/pull/157)).
 
-- Refresh the static capability snapshot to `command-code@1.87.0` and re-verify display pricing on 2026-10-21 for all 96 advertised models. MiniMax M3.1 Flash (paid and free) now supports image input, reasoning, and `low`/`medium`/`high`/`xhigh`/`max` efforts. Beam now supports reasoning with the same efforts and a 131,072-token output limit. Add paid and free Ornith 1.5 122B with image input and reasoning, without selectable efforts; paid rates are $0.16 input / $0.64 output / $0.02 cache read per million tokens, with no cache-write charge. Remove retired Cat Jam capability metadata. Extend the free MiniMax promotion to 2026-10-22T10:45:00Z and track the free Ornith promotion until 2026-10-22T06:00:00Z; both date-only guards require review from 2026-10-22 at 00:00 UTC, before either promotion ends. Existing paid rates and Beam's capacity-limited free pricing are unchanged.
-
-- Re-verify display pricing on 2026-10-20: add paid and free `minimax/minimax-m3.1-flash` entries and remove retired `stealth/cat-jam:free` pricing. The free MiniMax promotion ends on 2026-10-21 at 10:45 UTC; require a pricing recheck before that UTC day starts. The API now advertises 94 models. The CLI remains at `1.84.0` without MiniMax M3.1 Flash capability metadata, so both variants retain conservative text-only, non-reasoning defaults until upstream publishes it.
+### Contributors
 
-- Refresh the static capability snapshot to `command-code@1.84.0`, which publishes no model metadata changes, and add reviewed display pricing for the new free `reflection/beam:free` model, verified against the official pricing page on 2026-10-17. Beam is free only while capacity lasts, with no published expiry, and it has no CLI capability metadata yet, so it keeps the conservative text-only and non-reasoning defaults with a 65,536-token output limit. Reasoning and effort selection will become available after upstream publishes the required CLI metadata and the catalog snapshot is refreshed. The reviewed snapshot now covers all 93 advertised models.
-- Refresh the static capability snapshot to `command-code@1.83.0`: add image input, reasoning, and selectable `low`/`medium`/`high` efforts for `meta/muse-spark-open` and `nvidia/nemotron-3.5-super-vl`; publish reasoning for the free `stealth/cat-jam:free` preview with `low`/`medium`/`high`/`xhigh`/`max` efforts and a 131,072-token output limit. Retire `inclusionai/ling-3.0-flash-sante:free` and drop its reasoning flag, output limit, and display-price entry now that the API no longer advertises it. No prices changed; the reviewed snapshot now covers all 92 advertised models.
+- @sandexzx — refreshed the capability catalog and contributed the reviewed pricing for Beam, MiniMax M3.1 Flash and Ornith 1.5 122B ([#167](https://github.com/patlux/pi-commandcode-provider/pull/167), [#169](https://github.com/patlux/pi-commandcode-provider/pull/169)).
+- @pierreraby — independently verified the catalog, pricing and promotion-expiry deltas, and prepared this release.
 
 ## 0.7.8 - 2026-10-15
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-commandcode-provider",
-  "version": "0.7.8",
+  "version": "0.7.9",
   "description": "pi custom provider for Command Code API (commandcode.ai)",
   "type": "module",
   "keywords": [