baseline: official integration snapshot from verified local source tree

Author: CodeKing

.changeset/README.md

@@ -0,0 +1,8 @@
+# Changesets
+
+Hello and welcome! This folder has been automatically generated by `@changesets/cli`, a build tool that works
+with multi-package repos, or single-package repos to help you version and publish your code. You can
+find the full documentation for it [in our repository](https://github.com/changesets/changesets)
+
+We have a quick list of common questions to get you started engaging with this project in
+[our documentation](https://github.com/changesets/changesets/blob/main/docs/common-questions.md)

.changeset/add-editor-auto-close-settings.md

@@ -0,0 +1,5 @@
+---
+"zoo-code": minor
+---
+
+Add settings to control whether editor tabs Zoo opens during diff edits are auto-closed after accept/reject: auto-close transiently-opened files, auto-close even after user interaction (a refinement of the first), and auto-close newly created files.

.changeset/add-glm-5-2-support.md

@@ -0,0 +1,7 @@
+---
+"zoo-code": minor
+---
+
+Add GLM-5.2 support with High/Max `reasoning_effort` tiers. The default effort is High (deep reasoning stays opt-in), Max is selected only when the user explicitly picks it, and the parameter is omitted entirely when reasoning is disabled.
+
+Also refines the Opencode Go provider per review: bill MiniMax M3 cache writes (`cacheWritesPrice`), expose the max-output slider for DeepSeek V4 models (`supportsMaxTokens`), wrap pre-stream Anthropic-format errors with the provider prefix, and type the Anthropic streaming path's model info as `ModelInfo` so cost calculation can no longer silently return `$0`.

.changeset/api-request-timeout.md

@@ -0,0 +1,5 @@
+---
+"zoo-code": patch
+---
+
+Updated `apiRequestTimeout` validation. Values must be integers between 1 and 3600 seconds; invalid or out-of-range values, including `0`, now fall back to 600 seconds. This aligns with the SDK's default timeout value.

.changeset/changelog-config.js

@@ -0,0 +1,18 @@
+const getReleaseLine = async (changeset) => {
+	const lines = changeset.summary
+		.split("\n")
+		.map((l) => l.trim())
+		.filter(Boolean)
+	return lines.map((line) => (line.startsWith("- ") ? line : `- ${line}`)).join("\n")
+}
+
+const getDependencyReleaseLine = async () => {
+	return ""
+}
+
+const changelogFunctions = {
+	getReleaseLine,
+	getDependencyReleaseLine,
+}
+
+module.exports = changelogFunctions

.changeset/config.json

@@ -0,0 +1,11 @@
+{
+	"$schema": "https://unpkg.com/@changesets/config@3.0.4/schema.json",
+	"changelog": "./changelog-config.js",
+	"commit": false,
+	"fixed": [["zoo-code"]],
+	"linked": [],
+	"access": "restricted",
+	"baseBranch": "main",
+	"updateInternalDependencies": "patch",
+	"ignore": ["@roo-code/cli"]
+}

.changeset/fix-diff-scroll-position.md

@@ -0,0 +1,7 @@
+---
+"zoo-code": patch
+---
+
+Fix diff view scroll position and tab handling when applying edits. The diff now opens scrolled to the first changed line (including end-of-file removals, which are clamped to a valid line in the modified document) instead of forcing the viewport to the top. After accepting or rejecting a diff, files that were already open are restored to their pre-edit scroll position, and files that were not open before the edit have their transiently opened tab closed -- unless the user activated that tab during the diff, in which case it is kept open. Focus is no longer pulled back to the edited file when the user has navigated elsewhere. A file that was open in a preview tab is restored in a preview tab with the original scroll position, even if the target file replaced the preview tab and was automatically closed after the diff was accepted or rejected. A file that was pinned before the edit is re-pinned after the diff closes, so applying a diff no longer drops the tab's pinned state.
+
+When a user clicks or edits inside the diff pane, the target file's tab is kept open after saving -- even if it was not previously open. If the user only scrolls in the diff pane, the existing close behavior is preserved. When the target file is re-revealed after a diff, it scrolls to the position most recently viewed by the user: if the user last scrolled in the diff pane, the target file mirrors that scroll position; if the user last scrolled in the target file's own editor, that position is used instead; otherwise the pre-edit scroll position is restored.

.changeset/fix-litellm-model-desync.md

@@ -0,0 +1,28 @@
+---
+"zoo-code": patch
+---
+
+Fix LiteLLM provider cache key collision, credential priority, and model-selection fallback to non-existent default.
+
+Two bugs are addressed:
+
+1. **Cache key collision**: All URL-scoped providers (LiteLLM, Ollama, LM Studio, Poe, DeepSeek,
+   Requesty) previously shared one cache entry keyed only on the provider name. Switching between
+   profiles backed by different servers silently served the wrong model list and the stale list
+   persisted across VS Code restarts via the disk cache. Fixed with a compound cache key:
+   URL-scoped providers use `provider:baseUrl`; key-scoped providers (LiteLLM, Poe, Requesty)
+   additionally include a short, irreversible discriminator derived from the API key
+   (`provider:baseUrl:<discriminator>`) so that two different API keys on the same server never share
+   a cache entry (relevant when the server enforces per-key model allowlists). Both the discriminator
+   and the on-disk filename digest are derived via truncated PBKDF2 so neither can be reversed to
+   identify the API key written to the cache filename. The `RouterProvider.getModel()` cold-start
+   fallback is also corrected to pass the full options so it resolves the same compound key.
+
+2. **Silent fallback to hardcoded default**: When the LiteLLM model list was empty (due to the
+   collision above, a failed sync, or a transient error), `useSelectedModel` reset the configured
+   model ID to `claude-3-7-sonnet-20250219` -- a model that typically does not exist on user
+   LiteLLM servers. Four sub-fixes: preserve the configured model ID when the list is empty;
+   invalidate the React Query router-models cache after a successful "Sync Models" click; pass the
+   current LiteLLM credentials in the debounced `requestRouterModels` message; and correct the
+   credential priority in `webviewMessageHandler.ts` so that message values (current unsaved field
+   state) take precedence over stale saved config, matching the pattern already used for DeepSeek.

.changeset/fix-multiline-quoted-command-parsing.md

@@ -0,0 +1,17 @@
+---
+"zoo-code": patch
+---
+
+Fix command auto-approval for multi-line shell constructs that must be treated as a single command.
+
+**Quoted multi-line arguments** (`sh -c '...'`, `sh -c $'...'`, `sh -c "..."`): the parser previously split on every newline before handling quotes, so newlines inside a quoted argument were treated as separate commands, defeating allowlist auto-approval. Single-quoted, ANSI-C (`$'...'`), and double-quoted strings are now masked before the newline split so embedded newlines and operators stay within their command.
+
+**Heredocs** (`<< EOF`, `<< 'EOF'`, `<< "EOF"`, `<<- EOF`): the entire heredoc -- opener line, body, and terminator -- is now treated as a single quoted region. Body lines are not split into independent sub-commands. All heredoc delimiter quoting styles (unquoted, single-quoted, double-quoted, backslash-escaped) are supported. An unterminated heredoc (missing terminator) is treated as malformed and returned as a single opaque token.
+
+**Locale quoting** (`$"..."`): treated as a distinct token analogous to ANSI-C quoting, preserving the `$` prefix and preventing the double-quote handler from stripping it.
+
+Quote masking is comment-aware: a quote character inside a `#` comment is not paired with a quote on a later line, so a comment cannot hide a real newline separator and merge two distinct commands. Commands with an unterminated quote are detected with a quote-aware scanner and returned as a single opaque token, preventing a line inside the unclosed quote from surfacing as an independently auto-approvable command. Genuine unquoted newlines still split into separate sub-commands, each of which must be allowlisted for auto-approval.
+
+**Pattern selector (UI)**: the command pattern breakdown shown after execution now uses the same heredoc- and quote-aware parser (`parseCommand`) before extracting patterns, so an unterminated or terminated heredoc no longer produces spurious tokens like `EOF`, body-line words, or `<<` fragments in the allow/deny selector.
+
+Note: this change only prevents _auto-approval_ of fragments from a malformed command; it does not reject malformed commands before execution, which will be addressed in a separate PR to keep the scope focused here.

.changeset/improve-apply-diff-prompt.md

@@ -0,0 +1,5 @@
+---
+"zoo-code": patch
+---
+
+Enhance the `apply_diff` tool description and parameter instructions to recommend `:start_line:` with exact syntax and emphasize copy-paste exact matching requirements, improving success rates for Gemini Flash and other smaller/faster models.