owen/cassady
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Prepare v0.3.3 release
CI / Build (push) Waiting to run
CI / Test (push) Waiting to run

Browse Source
This commit is contained in:
owen
2026-06-25 19:48:48 -05:00
parent 52eca6477e
commit d05bb87a23
11 changed files with 92 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/providers.md
+2 -2
View File
@@ -96,9 +96,9 @@ Reasoning display is separate. `show_reasoning` controls whether provider-stream
Fast mode has two parts:
- `default_fast_mode` in `config.json`: the user's saved preference.
- `fast_mode.supported` in `models.json`: whether the active provider/model can honor that preference.
- `fast_mode.supported` in `models.json`: whether non-Codex provider/model metadata can honor that preference.
In v0.3.2, Cassady sends fast-mode requests only for `ChatGPT Codex`. Setup marks ChatGPT Codex model entries as fast-capable. OpenAI-compatible and custom model entries default to unsupported, so `/fast` can remember the preference without sending provider-specific fields.
Cassady sends fast-mode requests only for `ChatGPT Codex`. Any active `chatgpt-codex` provider model, including `gpt-5.5`, is treated as fast-capable so older model metadata does not block the feature. OpenAI-compatible and custom model entries default to unsupported, so `/fast` can remember the preference without sending provider-specific fields.
## Switching models