From 31eaef590e710e075aa6a3e2cc33f73e93833935 Mon Sep 17 00:00:00 2001 From: Mario Zechner Date: Mon, 13 Apr 2026 23:42:31 +0200 Subject: [PATCH] docs: audit unreleased changelog entries --- packages/ai/CHANGELOG.md | 6 ++++++ packages/coding-agent/CHANGELOG.md | 20 +++++++++++++++++--- packages/tui/CHANGELOG.md | 1 + 3 files changed, 24 insertions(+), 3 deletions(-) diff --git a/packages/ai/CHANGELOG.md b/packages/ai/CHANGELOG.md index 0452734fb..5243021f5 100644 --- a/packages/ai/CHANGELOG.md +++ b/packages/ai/CHANGELOG.md @@ -2,10 +2,16 @@ ## [Unreleased] +### Added + +- Added full `OpenRouterRouting` field support, including fallbacks, parameter requirements, data collection, ZDR, ignore lists, quantizations, provider sorting, max price, and preferred throughput and latency constraints ([#2904](https://github.com/badlogic/pi-mono/pull/2904) by [@zmberber](https://github.com/zmberber)) + ### Fixed - Bumped default Antigravity User-Agent version to `1.21.9` ([#2901](https://github.com/badlogic/pi-mono/pull/2901) by [@aadishv](https://github.com/aadishv)) - Fixed thinking levels for Gemma 4 models to use `thinkingLevel` and map Pi reasoning levels to the model's supported thinking levels ([#2903](https://github.com/badlogic/pi-mono/pull/2903) by [@aadishv](https://github.com/aadishv)) +- Fixed Gemini 2.5 Flash Lite minimal thinking budget to use the model's supported 512-token minimum instead of the regular Flash 128-token minimum, avoiding invalid thinking budget errors ([#2861](https://github.com/badlogic/pi-mono/pull/2861) by [@JasonOA888](https://github.com/JasonOA888)) +- Fixed OpenAI Codex Responses requests to forward configured `serviceTier` values, restoring service-tier selection for Codex sessions ([#2996](https://github.com/badlogic/pi-mono/pull/2996) by [@markusylisiurunen](https://github.com/markusylisiurunen)) ## [0.66.1] - 2026-04-08 diff --git a/packages/coding-agent/CHANGELOG.md b/packages/coding-agent/CHANGELOG.md index 5497fda0a..b58769351 100644 --- a/packages/coding-agent/CHANGELOG.md +++ b/packages/coding-agent/CHANGELOG.md @@ -2,12 +2,26 @@ ## [Unreleased] +### New Features + +- Full `openRouterRouting` support in `models.json`, including fallbacks, parameter requirements, data collection, ZDR, ignore lists, quantizations, provider sorting, max price, and preferred throughput and latency constraints. See [docs/models.md](docs/models.md). +- `PI_CODING_AGENT=true` environment variable set at startup so subprocesses can detect they are running inside the coding agent. + +### Added + +- Added full `openRouterRouting` field support in `models.json`, including fallbacks, parameter requirements, data collection, ZDR, ignore lists, quantizations, provider sorting, max price, and preferred throughput and latency constraints ([#2904](https://github.com/badlogic/pi-mono/pull/2904) by [@zmberber](https://github.com/zmberber)) +- Set `PI_CODING_AGENT=true` environment variable at startup so sub-processes can detect they are running inside the coding agent ([#2868](https://github.com/badlogic/pi-mono/issues/2868)) + ### Fixed - Updated `antigravity-image-gen.ts` example extension to use User-Agent version `1.21.9` ([#2901](https://github.com/badlogic/pi-mono/pull/2901) by [@aadishv](https://github.com/aadishv)) -### Added - -- Set `PI_CODING_AGENT=true` environment variable at startup so sub-processes can detect they are running inside the coding agent ([#2868](https://github.com/badlogic/pi-mono/issues/2868)) +- Bumped default Antigravity User-Agent version to `1.21.9` ([#2901](https://github.com/badlogic/pi-mono/pull/2901) by [@aadishv](https://github.com/aadishv)) +- Fixed Gemma 4 thinking level mapping to route between `MINIMAL` and `HIGH`, and map Pi reasoning levels to the model's supported thinking levels ([#2903](https://github.com/badlogic/pi-mono/pull/2903) by [@aadishv](https://github.com/aadishv)) +- Fixed Gemini 2.5 Flash Lite minimal thinking budget to use the model's supported 512-token minimum instead of the regular Flash 128-token minimum, avoiding invalid thinking budget errors ([#2861](https://github.com/badlogic/pi-mono/pull/2861) by [@JasonOA888](https://github.com/JasonOA888)) +- Fixed OpenAI Codex Responses requests to forward configured `serviceTier` values, restoring service-tier selection for Codex sessions ([#2996](https://github.com/badlogic/pi-mono/pull/2996) by [@markusylisiurunen](https://github.com/markusylisiurunen)) +- Fixed `Container.render()` stack overflow on long sessions by replacing `Array.push(...spread)` with a loop-based push, preventing `RangeError: Maximum call stack size exceeded` when child output exceeds the V8 call stack argument limit ([#2651](https://github.com/badlogic/pi-mono/issues/2651)) +- Fixed editor sticky-column tracking around paste markers so vertical cursor navigation restores the column from before the cursor entered a paste marker instead of jumping inside or past pasted content ([#3092](https://github.com/badlogic/pi-mono/pull/3092) by [@Perlence](https://github.com/Perlence)) +- Fixed queued messages typed during `/tree` branch summarization to flush automatically after navigation completes, so they no longer remain stuck in the steering queue ([#3091](https://github.com/badlogic/pi-mono/pull/3091) by [@Perlence](https://github.com/Perlence)) ## [0.66.1] - 2026-04-08 diff --git a/packages/tui/CHANGELOG.md b/packages/tui/CHANGELOG.md index ffe241e5d..5170a33ee 100644 --- a/packages/tui/CHANGELOG.md +++ b/packages/tui/CHANGELOG.md @@ -5,6 +5,7 @@ ### Fixed - Fixed `Container.render()` stack overflow on long sessions by replacing `Array.push(...spread)` with a loop-based push, preventing `RangeError: Maximum call stack size exceeded` when child output exceeds the V8 call stack argument limit ([#2651](https://github.com/badlogic/pi-mono/issues/2651)) +- Fixed editor sticky-column tracking around paste markers so vertical cursor navigation restores the column from before the cursor entered a paste marker instead of jumping inside or past pasted content ([#3092](https://github.com/badlogic/pi-mono/pull/3092) by [@Perlence](https://github.com/Perlence)) - Fixed TUI test suite failures caused by render throttle scheduling: added `VirtualTerminal.waitForRender()` helper that waits for the 16ms throttled render pipeline to settle before asserting viewport state ([#3076](https://github.com/badlogic/pi-mono/pull/3076) by [@aliou](https://github.com/aliou)) ## [0.66.1] - 2026-04-08