fix(models): support DeepSeek V4.1 vision and max effort
CI / typecheck (push) Failing after 51s
CI / format (push) Failing after 4s
CI / Oh My Pi compatibility (push) Failing after 1m7s
CI / CodeQL SAST (push) Failing after 26m15s
CI / Semgrep — pi extension audit (push) Failing after 8m15s
CI / Gitleaks — secrets scan (push) Failing after 8s
CI / Dependency review (push) Skipped
CI / npm audit (push) Failing after 6s
CI / Check lifecycle scripts (push) Failing after 2s

Refresh the generated capability catalog from command-code@1.44.0 to
1.53.1. deepseek/deepseek-v4.1-flash now advertises image input and its
low, high, and max reasoning efforts, so pi forwards attached images and
exposes the full thinking-level selector instead of reporting the model
as text-only without selectable levels. The sync also adds gpt-6-astra,
xai/grok-4.6, and inclusionai/ling-3.0-flash-sante:free metadata.

Drop the now-obsolete manual Meta Muse Spark effort overrides because
upstream publishes efforts for meta/muse-spark-1.1 through 1.3-contributor
and MiniMaxAI/MiniMax-M3, and add a regression test for the V4.1
capabilities.
This commit is contained in:
2026-09-13 22:27:51 +08:00
parent adea6585c0
commit 8007a6480c
5 changed files with 41 additions and 14 deletions
+3
View File
@@ -2,6 +2,9 @@
## Unreleased
- Refresh the generated Command Code capability catalog from `command-code@1.44.0` to `command-code@1.53.1`. `deepseek/deepseek-v4.1-flash` now advertises image input and its `low`, `high`, and `max` reasoning efforts, so pi forwards attached images and exposes the full thinking-level selector instead of the text-only, level-less defaults. New `gpt-6-astra`, `xai/grok-4.6`, and `inclusionai/ling-3.0-flash-sante:free` metadata comes along.
- Drop the now-obsolete manual Meta Muse Spark effort overrides: upstream ships efforts for `meta/muse-spark-1.1` through `1.3-contributor` and `MiniMaxAI/MiniMax-M3`, so `src/commandcode-catalog-overrides.ts` is empty.
## 0.6.4 - 2026-09-03
- Refresh the generated Command Code capability catalog from `command-code@1.40.1` to `command-code@1.44.0`, adding current image-input, reasoning, effort, and output-limit metadata for newly published models.