fix(ai): support xhigh for Codex GPT-5.5

This commit is contained in:
Mario Zechner
2026-04-23 22:49:09 +02:00
parent 8700ac1f0e
commit bf4aa3a601
7 changed files with 80 additions and 12 deletions

View File

@@ -24,6 +24,7 @@
### Fixed
- Fixed `--thinking xhigh` for `openai-codex` `gpt-5.5` so it is no longer downgraded to `high`.
- Fixed git package installs with custom `npmCommand` values such as `pnpm` by avoiding npm-specific production flags in that compatibility path ([#3604](https://github.com/badlogic/pi-mono/issues/3604))
- Fixed first user messages rendering without spacing after existing notices such as compaction summaries or status messages ([#3613](https://github.com/badlogic/pi-mono/issues/3613))
- Fixed the handoff extension example to use the replacement-session context after creating a new session, avoiding stale `ctx` errors when it installs the generated prompt ([#3606](https://github.com/badlogic/pi-mono/issues/3606))
@@ -37,6 +38,7 @@
- Fixed `ctx.ui.setWorkingMessage()` to persist across loader recreation, matching the behavior of `ctx.ui.setWorkingIndicator()` ([#3566](https://github.com/badlogic/pi-mono/issues/3566))
- Fixed coding-agent `fs.watch` error handling for theme and git-footer watchers to retry after transient watcher failures such as `EMFILE`, avoiding startup crashes in large repos ([#3564](https://github.com/badlogic/pi-mono/issues/3564))
- Fixed built-in `kimi-coding` model generation to attach the expected `User-Agent` header so direct Kimi Coding requests use the provider's expected client identity ([#3586](https://github.com/badlogic/pi-mono/issues/3586))
- Fixed `models.json` Anthropic-compatible provider configuration to accept `compat.supportsEagerToolInputStreaming`, allowing proxies that reject per-tool `eager_input_streaming` to use the legacy fine-grained tool streaming beta header instead ([#3575](https://github.com/badlogic/pi-mono/issues/3575))
## [0.69.0] - 2026-04-22