chore: fix changelog

2026-08-13 02:02:23 +02:00
parent e7e280a6fb
commit 4d73392621
4 changed files with 13 additions and 19 deletions
@@ -2,14 +2,15 @@

 ## [Unreleased]

+### Fixed
+
+- Manual `/shake` now keeps a small recent tail of tool results instead of stripping every eligible result, so the agent does not lose the context it is currently working from ([#7776](https://github.com/can1357/oh-my-pi/issues/7776)).
+
 ## [17.2.13] - 2026-08-11

 ### Fixed

 - Fixed Cursor sessions re-executing settled tools when an owned dialect projector rebuilds toolCall blocks: `snapshotAssistantContentBlock` now copies `kCursorExecResolved` explicitly so agent-loop still skips already-settled calls.
-### Fixed
-
- Manual `/shake` now keeps a small recent tail of tool results instead of stripping every eligible result, so the agent does not lose the context it is currently working from ([#7776](https://github.com/can1357/oh-my-pi/issues/7776)).

 ## [17.2.10] - 2026-08-06

@@ -15,6 +15,7 @@
 - Fixed `/login together` always failing with HTTP 400 `model_not_available`: key validation chat-completed against the hardcoded non-serverless model `moonshotai/Kimi-K2.5`, so no valid key could pass. Validation now probes Together's authenticated `/v1/models` listing, matching the model-agnostic approach used by other API-key providers ([#8328](https://github.com/can1357/oh-my-pi/issues/8328)).
 - Fixed aggregate usage fetches and credential-health probes sending reference-stored API keys (env var name, `!command`) as the literal reference string instead of the resolved secret, which would 401 and flag working credentials as bad for providers whose usage probe validates credentials ([#8337](https://github.com/can1357/oh-my-pi/pull/8337) by [@will-bogusz](https://github.com/will-bogusz)).
 - Fixed Perplexity email-OTP login dropping the session cookies required to verify the code ([#8156](https://github.com/can1357/oh-my-pi/issues/8156)).
+- Fixed OpenAI GPT-5.6 and Daybreak `off` thinking requests serializing as `low`; every first-party alias with explicit wire-level off support now sends `reasoning.effort: "none"`.

 ### Removed

@@ -51,7 +52,6 @@
 - Fixed the AWS credential resolver ignoring `role_arn` profiles: shared-config role chaining (`source_profile` recursion, `web_identity_token_file`, `credential_source`) now resolves via STS `AssumeRole`/`AssumeRoleWithWebIdentity`, honoring `role_session_name`/`duration_seconds`/`external_id`, so Bedrock is detected on EKS/IRSA and multi-account setups instead of reporting "No models available" ([#8209](https://github.com/can1357/oh-my-pi/issues/8209)).
 - Fixed Bedrock availability being under-detected on Nitro/EKS hosts: the EC2 metadata probe now recognizes Nitro DMI markers (`board_asset_tag` instance ids, `Amazon EC2` vendor fields) in addition to the Xen `ec2` UUID prefix ([#8209](https://github.com/can1357/oh-my-pi/issues/8209)).
 - Fixed DeepSeek Responses targets (opencode-go) rejecting a thinking-mode continuation with `400 The reasoning_text in the thinking mode must be passed back to the API` after a prewalk hand-off plus mid-run compaction: the Responses input builder re-encoded replayed assistant turns without a reasoning item, so the request enabled reasoning but shipped no `reasoning_text`. The encoder now synthesizes a `reasoning_text` reasoning item for every replayed assistant turn when the target requires reasoning replay in thinking mode (`requiresReasoningContentForAllAssistantTurns` / `requiresReasoningContentForToolCalls`), mirroring the chat-completions `reasoning_content` safety net ([#8248](https://github.com/can1357/oh-my-pi/issues/8248)).
- Fixed OpenAI GPT-5.6 and Daybreak `off` thinking requests serializing as `low`; every first-party alias with explicit wire-level off support now sends `reasoning.effort: "none"`.

 ## [17.2.12] - 2026-08-08

@@ -2,16 +2,14 @@

 ## [Unreleased]

-### Fixed
-
- Fixed Ollama Cloud DeepSeek V4 Flash (including dated/preview tags like `deepseek-v4-flash:0731`) exposing the generic `minimal`/`low`/`medium`/`high`/`xhigh` effort ladder without `max`; the `ollama-chat` transport now applies the DeepSeek effort contract (Flash → `low`/`high`/`max`, V4 Pro and older reasoners → `high`/`max`), matching the direct API and every other host ([#8334](https://github.com/can1357/oh-my-pi/issues/8334)).
- Bounded OpenAI-compatible model discovery with a default request timeout so a stalled provider `/models` endpoint can no longer hang startup indefinitely in `resolveModelDiscoveryFallback` ([#8315](https://github.com/can1357/oh-my-pi/issues/8315)).
 ### Added

 - Added first-party OpenAI Daybreak Blue, Daybreak Red, and GPT-5.6 Cyber models with their documented API pricing, token limits, tools, and full `off`/`low`/`medium`/`high`/`xhigh`/`max` reasoning controls.

 ### Fixed

+- Fixed Ollama Cloud DeepSeek V4 Flash (including dated/preview tags like `deepseek-v4-flash:0731`) exposing the generic `minimal`/`low`/`medium`/`high`/`xhigh` effort ladder without `max`; the `ollama-chat` transport now applies the DeepSeek effort contract (Flash → `low`/`high`/`max`, V4 Pro and older reasoners → `high`/`max`), matching the direct API and every other host ([#8334](https://github.com/can1357/oh-my-pi/issues/8334)).
+- Bounded OpenAI-compatible model discovery with a default request timeout so a stalled provider `/models` endpoint can no longer hang startup indefinitely in `resolveModelDiscoveryFallback` ([#8315](https://github.com/can1357/oh-my-pi/issues/8315)).
 - Fixed Codex-discovered `gpt-daybreak-*` aliases being treated as unknown models, restoring the GPT-5.6 `low`/`medium`/`high`/`xhigh`/`max` effort ladder and its 372K fallback only when the Codex registry omits `context_window`.
 - Fixed first-party OpenAI GPT-5.6 aliases to preserve wire-level `off` through generated pro aliases and to price requests above 272K input at each SKU's documented long-context rates.

@@ -2,6 +2,10 @@

 ## [Unreleased]

+### Added
+
+- Added Astral `ty` as a built-in Python primary LSP server (`ty server`), ordered behind `pyright`/`basedpyright`/`pylsp` so it becomes the primary Python LSP only when the existing servers are unavailable. `ruff` remains the Python linter and coexists alongside `ty` ([#4617](https://github.com/can1357/oh-my-pi/issues/4617)).
+
 ### Changed

 - `/usage`, `omp usage`, and the status line now show authoritative OpenCode Go quota from the official `GET /zen/go/v1/usage` endpoint — including usage made outside OMP — instead of dollar estimates summed from OMP-observed request costs. The status line renders all three windows (`5h` / `7d` / `mo`), and the per-turn cost recording special case for `opencode-go` sessions is gone along with the "OMP-observed spend only" disclaimer ([#8337](https://github.com/can1357/oh-my-pi/pull/8337) by [@will-bogusz](https://github.com/will-bogusz)).
@@ -42,9 +46,9 @@
 - Fixed agent-facing prompts mentioning tools that may be absent from the session catalog: `todo`/`grep` workflow guidance in the system prompt, `glob`/`read`/`edit` drill-in hints in the project prompt, `ask` directives in plan mode, and the orchestrate notice's `task`/`edit`/`write`/`lsp`/`bash`/`todo` budget are now gated on tool availability.
 - Fixed a `/skill:<name>` token embedded in a `/plan` or `/vibe` inline prompt being sent to the agent as literal text instead of loading the skill; mode-command inline prompts now dispatch skill invocations through the same custom-message path as the editor submit flow ([#8137](https://github.com/can1357/oh-my-pi/issues/8137)).
 - Fixed Codex reset fireworks triggering on ordinary weekly-usage decreases when the provider had not advanced the quota reset deadline.
-### Fixed
-
 - Fixed below-threshold tool turns waiting for asynchronous session persistence when no mid-run compaction will run, while preserving journal writes when a `message_end` listener fails and isolating notification-only handler payloads from late context mutations ([#8283](https://github.com/can1357/oh-my-pi/pull/8283) by [@ethancawse](https://github.com/ethancawse)).
+- Manual `/shake` now keeps a small recent tail of tool results instead of stripping every eligible result, so the agent does not lose the context it is currently working from ([#7776](https://github.com/can1357/oh-my-pi/issues/7776)).
+- Fixed Hindsight `per-project` and `per-project-tagged` scoping splitting one repository across two memory scopes when the checkout directory carries capitals: the project label is now lowercased, so a checkout at `~/code/General` writes and recalls under `project:general` like every other client of the same bank instead of opening a private `project:General` scope. **Migration note:** mixed-case checkouts previously stored memories under the case-preserving label (`per-project` bank id, `per-project-tagged` `project:<Name>` tags); after upgrading, those sessions read and write the lowercased scope, so memories retained under the old capitalized scope stay in the old bank/tag until re-retained there ([#8158](https://github.com/can1357/oh-my-pi/issues/8158)).

 ## [17.2.15] - 2026-08-12

@@ -132,15 +136,6 @@

 - Removed the `resolveAgentModelSource` model-resolver export, whose only use was being fed to `resolveExplicitModelRole`. Replaced by `resolveAgentModelSelection`, which returns the expanded `patterns` and the pre-expansion `role` together so a spawn path cannot derive one without the other ([#7910](https://github.com/can1357/oh-my-pi/pull/7910) by [@enieuwy](https://github.com/enieuwy)).
 - A run is now attributed to the model that actually produced its output, not whichever model the session was last pointed at. A retry fallback that errored on its first request — an exhausted quota, a hard provider error — was credited with the whole run in the Agent Hub row and the settled task result, even when the previous model did every turn. Sessions expose the serving model directly, holding the last model that produced output while a candidate is armed but unproven, and transcript-derived history stops at the newest turn that produced output.
-### Fixed
-
- Manual `/shake` now keeps a small recent tail of tool results instead of stripping every eligible result, so the agent does not lose the context it is currently working from ([#7776](https://github.com/can1357/oh-my-pi/issues/7776)).
-### Fixed
-
- Fixed Hindsight `per-project` and `per-project-tagged` scoping splitting one repository across two memory scopes when the checkout directory carries capitals: the project label is now lowercased, so a checkout at `~/code/General` writes and recalls under `project:general` like every other client of the same bank instead of opening a private `project:General` scope.
-### Added
-
- Added Astral `ty` as a built-in Python primary LSP server (`ty server`), ordered behind `pyright`/`basedpyright`/`pylsp` so it becomes the primary Python LSP only when the existing servers are unavailable. `ruff` remains the Python linter and coexists alongside `ty` ([#4617](https://github.com/can1357/oh-my-pi/issues/4617)).

 ## [17.2.12] - 2026-08-08