diff --git a/packages/catalog/CHANGELOG.md b/packages/catalog/CHANGELOG.md
index 9d0ce85e4..cfbcd4424 100644
--- a/packages/catalog/CHANGELOG.md
+++ b/packages/catalog/CHANGELOG.md
@@ -10,6 +10,9 @@
 
 - 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)).
 - Fixed the model cache (`models.db`) serializing provider-defined request headers written into a model's `headers` — any custom name can carry a credential (for example `Authorization`, `X-Goog-Api-Key`, or `X-Access-Token`), so a denylist cannot make plaintext persistence safe. `writeModelCache` now omits all model headers and records only the ids whose headers were removed. On read, schema v10 restores matching static-model headers from the caller's live source; dynamic-only models with omitted headers force an online refetch and are excluded from offline/failure fallbacks rather than returned unusable. Older header-bearing rows are invalidated and securely deleted so their values do not remain recoverable in SQLite free pages ([#5780](https://github.com/can1357/oh-my-pi/issues/5780)).
+- Fixed OpenAI Codex discovery to replace stale bundled models with the authenticated account catalog, preventing unsupported models from remaining selectable. ([#5364](https://github.com/can1357/oh-my-pi/issues/5364))
+- Fixed OpenAI Codex discovery ignoring the caller-supplied `fetch`, so it always hit the global network instead of the configured (proxy/extra-CA/test) fetch. ([#5364](https://github.com/can1357/oh-my-pi/issues/5364))
+- Fixed a loopback `litellm` proxy fronting a local llama.cpp/vLLM server aborting long prefills with `stream timed out while waiting for the first event` and retry-looping. `litellm` is excluded from `isLocalOpenAICompatBackend` to keep `replayReasoningContent` off proxies (which could 400 an unrelated cloud upstream), but that exclusion also stripped the 300s local stream-timeout floor, leaving the 100s default; a slow reprocess (llama.cpp `non-consecutive token position` KV thrash) then exceeded it. The timeout floor now applies to any loopback/RFC1918 backend, including proxies, while reasoning replay stays gated to first-party local providers. ([#4786](https://github.com/can1357/oh-my-pi/issues/4786))
 
 ## [17.0.4] - 2026-07-18
 
@@ -78,10 +81,6 @@
 - Fixed reasoning effort mapping for Z.ai GLM-5.2 on the Anthropic messages endpoint to correctly use the two-tier scale (high, max) and emit output_config.effort.
 - Fixed an issue where stale cached model limits would override updated static catalog limits after a catalog fingerprint mismatch.
 - Fixed Cursor discovery to correctly preserve GetUsableModels max-mode metadata for premium models and invalidate stale cache entries.
-### Fixed
-
-- Fixed OpenAI Codex discovery to replace stale bundled models with the authenticated account catalog, preventing unsupported models from remaining selectable. ([#5364](https://github.com/can1357/oh-my-pi/issues/5364))
-- Fixed OpenAI Codex discovery ignoring the caller-supplied `fetch`, so it always hit the global network instead of the configured (proxy/extra-CA/test) fetch. ([#5364](https://github.com/can1357/oh-my-pi/issues/5364))
 
 ## [16.4.3] - 2026-07-11
 
@@ -182,9 +181,6 @@
 - Fixed LiteLLM discovery stopping at `/model_group/info` when that endpoint omitted `supports_vision`; it now continues to `/model/info` and preserves `model_info.supports_vision=true` for vision-capable proxy models. ([#4747](https://github.com/can1357/oh-my-pi/issues/4747))
 - Fixed LiteLLM discovery to fall back to bundled catalog metadata when `models.dev` lacks a model reference, preserving reasoning and thinking support for models such as `glm-5.2`. ([#4695](https://github.com/can1357/oh-my-pi/issues/4695))
 - Detected Azure AI Inference / Foundry Anthropic routes as strict-tool-incompatible so resolved Anthropic compat disables strict tools before request construction ([#4679](https://github.com/can1357/oh-my-pi/issues/4679)).
-### Fixed
-
-- Fixed a loopback `litellm` proxy fronting a local llama.cpp/vLLM server aborting long prefills with `stream timed out while waiting for the first event` and retry-looping. `litellm` is excluded from `isLocalOpenAICompatBackend` to keep `replayReasoningContent` off proxies (which could 400 an unrelated cloud upstream), but that exclusion also stripped the 300s local stream-timeout floor, leaving the 100s default; a slow reprocess (llama.cpp `non-consecutive token position` KV thrash) then exceeded it. The timeout floor now applies to any loopback/RFC1918 backend, including proxies, while reasoning replay stays gated to first-party local providers. ([#4786](https://github.com/can1357/oh-my-pi/issues/4786))
 
 ## [16.3.11] - 2026-07-06
 
diff --git a/packages/coding-agent/CHANGELOG.md b/packages/coding-agent/CHANGELOG.md
index adb2e3886..ed0539025 100644
--- a/packages/coding-agent/CHANGELOG.md
+++ b/packages/coding-agent/CHANGELOG.md
@@ -95,11 +95,16 @@
 - Fixed LSP requests silently clamping explicit timeouts above 60 seconds by supporting documented budgets up to 300 seconds ([#5804](https://github.com/can1357/oh-my-pi/issues/5804)).
 - Clarified async task and hub guidance: inspecting a settled job consumes its automatic delivery, job IDs expire from process memory after roughly five minutes, and completion does not verify claimed artifacts ([#5869](https://github.com/can1357/oh-my-pi/issues/5869)).
 - Fixed `vibe_wait` TV-wall panels stacking duplicate frozen frames in native scrollback while two or more workers were live ([#5777](https://github.com/can1357/oh-my-pi/issues/5777)).
+- Fixed async task job rows omitting resolved subagent model and reasoning badges when `task.showResolvedModelBadge` is enabled. ([#5060](https://github.com/can1357/oh-my-pi/issues/5060))
+- Fixed raw Puppeteer `page`/`browser` promises from crashing inline browser workers or killing dedicated workers when a target closed before the caller awaited the promise.
+- Fixed auto-compaction dead-ending in a warning loop ("Compaction freed too little context to make progress") when the single most-recent turn is itself over budget so `prepareCompaction` has nothing to summarize (`findCutPoint` never cuts inside a tool result). This `!preparation` short-circuit never ran the artifact-backed `shake` elide rescue that #3786 added to the post-maintenance guard, so snapcompact/context-full maintenance paused with no attempt to shrink the oversized tail. The dead-end now runs the same elide pass, re-prepares on the shrunken branch, and falls through to a normal compaction when the tail became summarizable — only pausing (single warning) when nothing is elide-eligible. ([#4786](https://github.com/can1357/oh-my-pi/issues/4786))
+- Fixed GitHub-hosted repository file reads falling back to `curl` by adding a dedicated `github` file-read operation and explicit tool-routing guidance ([#4805](https://github.com/can1357/oh-my-pi/issues/4805)).
 
 ### 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))
+- Fixed authoritative providers (e.g. `openai-codex`) keeping unsupported bundled models selectable when a fresh model cache and an expired OAuth token coincided: built-in discovery now forces the OAuth refresh so the provider's model manager is constructed and prunes stale bundled entries (e.g. `gpt-5.4-nano`) instead of waiting out the cache TTL. ([#5364](https://github.com/can1357/oh-my-pi/issues/5364))
 
 ## [17.0.4] - 2026-07-18
 
@@ -259,7 +264,6 @@
 - Fixed launch tool rendering stacking a stale pending header over a bare `✓ Launch` line and raw text: the tool now uses a merged registry renderer with one per-op status header (op, target, `state · pid · uptime` meta), stripped log cursor suffixes, capped collapsed log/list previews, and a launch tool glyph
 - Fixed confusing launch start/wait results when readiness timed out with the log pattern already matched (readiness needs log AND port): the result printed a contradictory `Ready: <match>` next to `Readiness timed out` without naming the failing condition. Daemon snapshots now carry the unmet conditions (`readyPending`), and start/wait results state exactly what never happened (e.g. `port 3100 on 127.0.0.1 never accepted connections`); the TUI shows a `waiting on port` badge on starting daemons
 - Fixed the in-process `stat` builtin mangling BSD-style invocations like `stat -f "%Sm %N" file` (macOS muscle memory): GNU `-f` means `--file-system`, so the format string was treated as a file operand — printing filesystem info for the real operands and erroring with `cannot read file system information for '%Sm %N'`. A `-f` whose format value contains `%` is now detected as BSD syntax and translated to the GNU equivalent (`%Sm`→`%y`, `%N`→`%n`, `%z`→`%s`, epoch/`S`-form times, owner/group/permission and `H`/`L` sub-field directives, `-L`/`-n`/`-q`/`-F` flag clusters, with `%n`/`%t` as literal newline/tab); directives with no GNU counterpart fail with a clear `unsupported BSD format directive` error
-- Fixed authoritative providers (e.g. `openai-codex`) keeping unsupported bundled models selectable when a fresh model cache and an expired OAuth token coincided: built-in discovery now forces the OAuth refresh so the provider's model manager is constructed and prunes stale bundled entries (e.g. `gpt-5.4-nano`) instead of waiting out the cache TTL. ([#5364](https://github.com/can1357/oh-my-pi/issues/5364))
 - Fixed the remaining GNU-flavored shell builtins that broke under macOS/BSD muscle memory, using the same unambiguous-detection approach as the `stat` fix (only invocations that are invalid or nonsensical under GNU semantics are reinterpreted; unsupported BSD forms fail loudly instead of producing wrong output): `date -r <epoch>` formats the epoch when no such file exists (GNU `-r FILE` mtime preserved), signed `date -v±N<unit>` adjustments translate to `-d` relative dates and `-j` is accepted (`-j -f` strptime parse mode and field-set `-v` error clearly); `sed -i '' 's/…/…/' file` drops the BSD empty backup-suffix token instead of treating it as the script; `mktemp -t prefix` without X's creates `$TMPDIR/prefix.XXXXXXXXXX` (the GNU `too few X's` error path); `tail -r` reverses input by delegating to `tac` (with `-n`/`-c`/`-f` combinations erroring clearly); `find -E` maps to `-regextype posix-extended` ahead of the expression; `base64 -D` decodes as an alias of `-d`; and `ln -sfh` works via a `-h` alias of `--no-dereference` (clap's `-h` help short is dropped to match real GNU/BSD ln; `--help` unchanged)
 - Fixed the browser tool crashing the whole process (parent session and every subagent) when a CDP world re-acquire failed mid-navigation: the stealth `puppeteer-core` patch called the bare `debugError` logger, which is `undefined` while the `puppeteer:error` debug channel is disabled (the default), turning a transient acquire failure into a fatal `TypeError` unhandled rejection. The patched `FrameManager`/`WebWorker` acquire paths now use `debugCatchError` ([#5296](https://github.com/can1357/oh-my-pi/issues/5296))
 - Fixed a role with a `:high` thinking suffix resolving to a longer sibling model whose id embeds the tier name (e.g. `kimi-for-coding:high` → `kimi-for-coding-highspeed`). The thinking suffix is now stripped before any fuzzy match, so `provider/model:high` keeps the exact model at high effort ([#5151](https://github.com/can1357/oh-my-pi/issues/5151)).
@@ -273,8 +277,6 @@
 - Fixed xAI web search bypassing configured `xai` / `xai-oauth` proxy endpoints and headers, while preventing official OAuth tokens from being sent to custom endpoints ([#5599](https://github.com/can1357/oh-my-pi/issues/5599)).
 - Fixed `models.yml` rejecting the Anthropic `compat.supportsEagerToolInputStreaming` override for custom endpoints ([#5572](https://github.com/can1357/oh-my-pi/issues/5572)).
 - Fixed long streamed table responses duplicating in terminal scrollback when later rows widened an earlier column.
-- Fixed async task job rows omitting resolved subagent model and reasoning badges when `task.showResolvedModelBadge` is enabled. ([#5060](https://github.com/can1357/oh-my-pi/issues/5060))
-- Fixed raw Puppeteer `page`/`browser` promises from crashing inline browser workers or killing dedicated workers when a target closed before the caller awaited the promise.
 - Fixed Bash internal URLs remaining unresolved when used as unquoted arguments inside command substitutions ([#5535](https://github.com/can1357/oh-my-pi/issues/5535)).
 - Fixed the built-in `fd` printing `fd: Broken pipe (os error 32)` when a downstream pipeline reader exited early (e.g. `fd … | head`); it now exits silently with 141 (128+SIGPIPE), matching real fd.
 - Fixed prewalk repeatedly continuing after a bash-only task such as `commit` had already completed ([#5551](https://github.com/can1357/oh-my-pi/issues/5551)).
@@ -776,8 +778,6 @@
 - Fixed retry fallback model recovery by exposing `retry.fallbackChains` in `/settings`, adding a `/model` action to assign the selected default fallback model, and clearing a selected model's retry cooldown marker on manual model switches. ([#4533](https://github.com/can1357/oh-my-pi/issues/4533))
 - Fixed `/handoff` and auto-handoff skipping extension lifecycle hooks by emitting cancellable `session_before_switch` hooks and a `session_switch` with `reason: "handoff"` after the replacement session is ready ([#4434](https://github.com/can1357/oh-my-pi/issues/4434)).
 - Fixed TTSR stream interrupts so only the tool call whose stream matched a rule receives the rule-named abort result; sibling tool-call placeholders now use a neutral abort reason ([#2783](https://github.com/can1357/oh-my-pi/issues/2783)).
-- Fixed auto-compaction dead-ending in a warning loop ("Compaction freed too little context to make progress") when the single most-recent turn is itself over budget so `prepareCompaction` has nothing to summarize (`findCutPoint` never cuts inside a tool result). This `!preparation` short-circuit never ran the artifact-backed `shake` elide rescue that #3786 added to the post-maintenance guard, so snapcompact/context-full maintenance paused with no attempt to shrink the oversized tail. The dead-end now runs the same elide pass, re-prepares on the shrunken branch, and falls through to a normal compaction when the tail became summarizable — only pausing (single warning) when nothing is elide-eligible. ([#4786](https://github.com/can1357/oh-my-pi/issues/4786))
-- Fixed GitHub-hosted repository file reads falling back to `curl` by adding a dedicated `github` file-read operation and explicit tool-routing guidance ([#4805](https://github.com/can1357/oh-my-pi/issues/4805)).
 
 ## [16.3.11] - 2026-07-06