chore: normalized changelog sections after merges

packages/ai/CHANGELOG.md

@@ -1,9 +1,6 @@
 # Changelog
 
 ## [Unreleased]
-### Fixed
-
-- Retry one transient OpenAI Responses stream truncation before replay-unsafe output, preventing recoverable transport truncations from surfacing as failed turns ([#5908](https://github.com/can1357/oh-my-pi/issues/5908)).
 
 ### Changed
 
@@ -11,10 +8,13 @@
 
 ### Fixed
 
+- Retry one transient OpenAI Responses stream truncation before replay-unsafe output, preventing recoverable transport truncations from surfacing as failed turns ([#5908](https://github.com/can1357/oh-my-pi/issues/5908)).
 - Kept native Kimi Code K3 thinking enabled for named function selection by using generic required tool choice.
 - Fixed `/login moonshot` validating China-platform API keys against the international host instead of honoring `MOONSHOT_BASE_URL` ([#5981](https://github.com/can1357/oh-my-pi/issues/5981)).
 - Fixed Anthropic session credential stickiness suppressing usage-based re-ranking indefinitely: the session pin skipped ranking for up to 30 days (or process lifetime) even after the ≤1h prompt cache it protects was no longer guaranteed warm. The Anthropic skip is now gated on time since the session's last resolve (`ANTHROPIC_SESSION_STICKY_CACHE_WARM_MS`, 1h), while providers without a verified cache lifetime retain their existing stickiness. When ranking runs, the pinned account is only a tie-break rather than an absolute front-of-queue override, restoring proactive multi-account load balancing after long idle ([#5966](https://github.com/can1357/oh-my-pi/issues/5966)).
 - Fixed clockless Anthropic usage windows outranking clocked sibling credentials by scoring their headroom over the full window duration ([#5960](https://github.com/can1357/oh-my-pi/issues/5960)).
+- Fixed local grammar-constrained OpenAI-compatible backends (llama.cpp, LM Studio, vLLM) rejecting every tool request with `400 "Unable to generate parser for this template ... Unrecognized schema: true"`. The `task` tool's open `outputSchema` field normalizes to a bare boolean `true` subschema (issue #1179), which llama.cpp's JSON-schema→GBNF converter cannot compile. The chat-completions encoder now widens bare boolean subschemas into a value-accepting primitive union (and preserves closed-object `additionalProperties: false`) for these backends via the new `grammar` tool-schema flavor ([#5914](https://github.com/can1357/oh-my-pi/issues/5914)).
+- Fixed custom OAuth Anthropic-compatible endpoints with explicit header overrides still receiving generated Claude Code fingerprint headers instead. ([#5888](https://github.com/can1357/oh-my-pi/issues/5888))
 
 ## [17.0.4] - 2026-07-18
 
@@ -24,10 +24,6 @@
 - Made Kimi device-id persistence best-effort: a missing or unwritable `~/.omp/agent` directory no longer throws during Kimi header construction, which silently nulled every `kimi-code` usage probe on fresh installs.
 - Coerced boolean tool-schema subschemas to MFJS object forms for native Moonshot/Kimi endpoints, preventing the task tool's `outputSchema` field from causing HTTP 400 responses ([#5952](https://github.com/can1357/oh-my-pi/issues/5952)).
 
-### Fixed
-
-- Fixed local grammar-constrained OpenAI-compatible backends (llama.cpp, LM Studio, vLLM) rejecting every tool request with `400 "Unable to generate parser for this template ... Unrecognized schema: true"`. The `task` tool's open `outputSchema` field normalizes to a bare boolean `true` subschema (issue #1179), which llama.cpp's JSON-schema→GBNF converter cannot compile. The chat-completions encoder now widens bare boolean subschemas into a value-accepting primitive union (and preserves closed-object `additionalProperties: false`) for these backends via the new `grammar` tool-schema flavor ([#5914](https://github.com/can1357/oh-my-pi/issues/5914)).
-
 ## [17.0.3] - 2026-07-17
 
 ### Fixed
@@ -39,10 +35,6 @@
 - Automatically invalidate and rotate OAuth credentials when an "invalidated oauth token" error occurs
 - Fixed Anthropic usage reports treating the organization response header as the account identity, which caused the 5h/7d status-line segment to disappear for OAuth credentials without stored organization metadata. ([#5698](https://github.com/can1357/oh-my-pi/issues/5698))
 
-### Fixed
-
-- Fixed custom OAuth Anthropic-compatible endpoints with explicit header overrides still receiving generated Claude Code fingerprint headers instead. ([#5888](https://github.com/can1357/oh-my-pi/issues/5888))
-
 ## [17.0.2] - 2026-07-17
 
 ### Fixed

packages/catalog/CHANGELOG.md

@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Added
+
+- Added an Anthropic compatibility flag for opting non-official OAuth endpoints into configured Claude Code fingerprint header overrides. ([#5888](https://github.com/can1357/oh-my-pi/issues/5888))
+
 ### Fixed
 
 - Fixed Kimi K3 models served through generic OpenAI-compatible routes exposing unsupported reasoning efforts instead of the mandatory `low`/`high`/`max` scale ([#5983](https://github.com/can1357/oh-my-pi/issues/5983)).
@@ -19,9 +23,6 @@
 - Logged LiteLLM rich-metadata endpoint failures once with their endpoint and status before falling back to incomplete `/v1/models` data ([#5801](https://github.com/can1357/oh-my-pi/issues/5801)).
 - Fixed authenticated Kimi Code discovery to preserve live effort levels, default effort, mandatory-thinking state, and per-model protocol metadata ([#5893](https://github.com/can1357/oh-my-pi/issues/5893)).
 - Fixed LiteLLM provider ignoring per-model pricing: `mapLiteLLMRichEntry` now reads `input_cost_per_token` / `output_cost_per_token` (plus cache costs) from LiteLLM rich metadata and maps them to `cost.input` / `cost.output`, falling back to the bundled reference only when LiteLLM omits cost, so proxied models no longer display as free ([#5818](https://github.com/can1357/oh-my-pi/issues/5818)).
-### Added
-
-- Added an Anthropic compatibility flag for opting non-official OAuth endpoints into configured Claude Code fingerprint header overrides. ([#5888](https://github.com/can1357/oh-my-pi/issues/5888))
 
 ## [17.0.2] - 2026-07-17
 

packages/coding-agent/CHANGELOG.md

@@ -2,6 +2,13 @@
 
 ## [Unreleased]
 
+### Changed
+
+- Reduced concurrent subagent update CPU by reconstructing recent output only at progress emission boundaries. ([#5936](https://github.com/can1357/oh-my-pi/issues/5936))
+- Fixed `docs/advisor-watchdog.md` overstating advisor delivery for a normal yield: the severity table listed `concern` as unconditionally interrupting and the prose promised a self-ended run could always be steered/resumed. Documented the #4840 terminal-answer exception (`concern` becomes a passive card while `blocker` normally steers, #5628) plus the plan-mode and deferred-ACP constraints that preserve would-be steers until the user resumes ([#5913](https://github.com/can1357/oh-my-pi/issues/5913)).
+- Fixed subagent (task) sessions triggering an unnecessary tiny-model session-title generation call on `todo init`. Subagent sessions in a non-interactive host (print/RPC/ACP/eval/SDK/CI) have no operator-visible title and now skip the replan title refresh; interactive hosts keep it, since a live subagent focused from the Agent Hub renders its session name in the status line ([#5910](https://github.com/can1357/oh-my-pi/issues/5910)).
+- Fixed `tab.scroll()` timing out after a queued wheel event waits too long for a busy renderer's acknowledgement ([#5905](https://github.com/can1357/oh-my-pi/issues/5905)).
+
 ### Fixed
 
 - Fixed `--model <role>` resolving a bare configured `modelRoles` key.
@@ -21,6 +28,14 @@
 - Fixed headless print mode disposing the session before a final advisor review completed, which could drop the advisor transcript and usage ([#5942](https://github.com/can1357/oh-my-pi/pull/5942)).
 - Fixed capped zero-block assistant stops remaining in active/session history with the full failed-request usage, causing the next post-snapcompact `continue` to re-enter context maintenance at the same boundary; capped empty turns are now discarded and the failure names model switching or `/shake images` as recovery options ([#5959](https://github.com/can1357/oh-my-pi/issues/5959)).
 - Long sessions no longer re-run `convertToLlm` over settled history every turn. Conversion is memoized per message identity (plus the assistant `interruptedNext` neighbor flag): an exact re-convert of the same array reuses the outer `Message[]`, append-only growth reuses the converted prefix via slice-on-growth, and the prune/shake/strip-images/prewalk-scrub rewrite seams invalidate the affected message before the next pass. On the `llm-assembly` bench (N=5000) steady/append convert and repeat estimate are all >10x faster with robust MAD-noise well under 20% ([#5934](https://github.com/can1357/oh-my-pi/issues/5934)).
+- Fixed `/exit` hanging on post-prompt work and stacking independent subsystem teardown delays by bounding the aborted-work drain, disposing independent session resources concurrently, and keeping long shutdown waits visible ([#5932](https://github.com/can1357/oh-my-pi/issues/5932)).
+- Fixed queued-message display updates being skipped by focused-editor keystroke frames by explicitly repainting the pending-message container ([#5928](https://github.com/can1357/oh-my-pi/issues/5928)).
+- Fixed RPC and RPC-UI startup crashes when an in-process extension claimed Bun's singleton stdin stream before the protocol reader ([#5898](https://github.com/can1357/oh-my-pi/issues/5898)).
+
+### Removed
+
+- Fixed the Cursor-backed advisor losing entire turns when it selected server-native tools (`bash`, `grep`, etc.) outside its grant: exec-resolved native blocks are already rejected in-band by the advisor-scoped bridge, so they no longer trip the unavailable-tool quarantine and discard the `advise` emitted in the same turn ([#5900](https://github.com/can1357/oh-my-pi/issues/5900)).
+- Fixed custom `anthropic-messages` OAuth providers being unable to opt into configured Claude Code fingerprint header overrides. ([#5888](https://github.com/can1357/oh-my-pi/issues/5888))
 
 ## [17.0.4] - 2026-07-18
 
@@ -31,13 +46,6 @@
 - Fixed `task` tool schemas emitting boolean subschemas that llama.cpp grammar generation cannot parse ([#5957](https://github.com/can1357/oh-my-pi/issues/5957)).
 - Fixed the transcript keeping finalized assistant blocks in the live compose walk after their rows entered native terminal scrollback, making each stream tick's `TranscriptContainer.render` depth-linear in session length. Fully committed finalized blocks are now compacted out of the local frame regardless of post-finalize version tracking; a later mutation no longer recommits on ordinary frames (no duplication) and rehydrates on the next destructive full replay (no loss). Compose cost for a live tail tick is now flat as depth grows (`bench/transcript-compose.bench.ts`: ratio(N5000/N500) 2.30 → 0.90) ([#5930](https://github.com/can1357/oh-my-pi/issues/5930)).
 - Fixed `/quit` and `/exit` hanging during interactive shutdown by making the mnemopi dispose path retain the current session and flush in-flight extractions without sleeping the bank; the `/memory enqueue` path and end-of-session backend enqueue still perform full cross-session consolidation. ([#3641](https://github.com/can1357/oh-my-pi/issues/3641))
-- Fixed `/exit` hanging on post-prompt work and stacking independent subsystem teardown delays by bounding the aborted-work drain, disposing independent session resources concurrently, and keeping long shutdown waits visible ([#5932](https://github.com/can1357/oh-my-pi/issues/5932)).
-### Changed
-
-- Reduced concurrent subagent update CPU by reconstructing recent output only at progress emission boundaries. ([#5936](https://github.com/can1357/oh-my-pi/issues/5936))
-- Fixed `docs/advisor-watchdog.md` overstating advisor delivery for a normal yield: the severity table listed `concern` as unconditionally interrupting and the prose promised a self-ended run could always be steered/resumed. Documented the #4840 terminal-answer exception (`concern` becomes a passive card while `blocker` normally steers, #5628) plus the plan-mode and deferred-ACP constraints that preserve would-be steers until the user resumes ([#5913](https://github.com/can1357/oh-my-pi/issues/5913)).
-- Fixed subagent (task) sessions triggering an unnecessary tiny-model session-title generation call on `todo init`. Subagent sessions in a non-interactive host (print/RPC/ACP/eval/SDK/CI) have no operator-visible title and now skip the replan title refresh; interactive hosts keep it, since a live subagent focused from the Agent Hub renders its session name in the status line ([#5910](https://github.com/can1357/oh-my-pi/issues/5910)).
-- Fixed `tab.scroll()` timing out after a queued wheel event waits too long for a busy renderer's acknowledgement ([#5905](https://github.com/can1357/oh-my-pi/issues/5905)).
 
 ## [17.0.3] - 2026-07-17
 
@@ -59,7 +67,6 @@
 
 ### Fixed
 
-- Fixed queued-message display updates being skipped by focused-editor keystroke frames by explicitly repainting the pending-message container ([#5928](https://github.com/can1357/oh-my-pi/issues/5928)).
 - Fixed `xd://` mount notices triggering unsolicited model turns by deferring hidden notices until the next user prompt.
 - Fixed `xd://` device tools appearing in the direct tool inventory and prompting invalid function calls ([#5797](https://github.com/can1357/oh-my-pi/issues/5797)).
 - Fixed `history://` read selectors being treated as part of the agent id instead of paging the transcript ([#5806](https://github.com/can1357/oh-my-pi/issues/5806)).
@@ -83,8 +90,6 @@
 ### Removed
 
 - Removed the unreliable Bing and Yahoo HTML-scraping web search providers
-- Fixed the Cursor-backed advisor losing entire turns when it selected server-native tools (`bash`, `grep`, etc.) outside its grant: exec-resolved native blocks are already rejected in-band by the advisor-scoped bridge, so they no longer trip the unavailable-tool quarantine and discard the `advise` emitted in the same turn ([#5900](https://github.com/can1357/oh-my-pi/issues/5900)).
-- Fixed custom `anthropic-messages` OAuth providers being unable to opt into configured Claude Code fingerprint header overrides. ([#5888](https://github.com/can1357/oh-my-pi/issues/5888))
 
 ## [17.0.2] - 2026-07-17
 
@@ -110,7 +115,6 @@
 
 ### Fixed
 
-- Fixed RPC and RPC-UI startup crashes when an in-process extension claimed Bun's singleton stdin stream before the protocol reader ([#5898](https://github.com/can1357/oh-my-pi/issues/5898)).
 - Fixed loading issues for linked legacy extensions importing `DefaultPackageManager` or `linkedom`.
 - Fixed the advisor retrying terminal, non-retriable provider failures (e.g., blocked prompts), ensuring they fail immediately while transient failures still retry.
 - Fixed an issue where reassigning the `plan` role model mid-planning did not take effect until the next plan-mode entry; it now applies at the next turn boundary.

packages/tui/CHANGELOG.md

@@ -2,13 +2,14 @@
 
 ## [Unreleased]
 
-### Fixed
-
-- Fixed ordinary coding-agent editor keystrokes performing a full root compose by adding an explicit stable-focus subtree-render opt-in while preserving full composition for callback-driven components and focus changes ([#5928](https://github.com/can1357/oh-my-pi/issues/5928)).
 ### Changed
 
 - Carried validated line widths through text, box, editor, and frame layout to avoid repeated Unicode width measurement. ([#5938](https://github.com/can1357/oh-my-pi/issues/5938))
 
+### Fixed
+
+- Fixed ordinary coding-agent editor keystrokes performing a full root compose by adding an explicit stable-focus subtree-render opt-in while preserving full composition for callback-driven components and focus changes ([#5928](https://github.com/can1357/oh-my-pi/issues/5928)).
+
 ## [17.0.3] - 2026-07-17
 
 ### Fixed