3.29.3

docs/features/settings-management.md

@@ -146,7 +146,37 @@ Use this option only if you are certain you want to remove all Roo Code data or
 
 ---
 
-## Related UI Setting: Collapse thinking messages by default
+## UI Setting
+
+#### System Prompt Context Toggles
+
+Control what contextual information appears in the system prompt:
+
+- **Include Current Time** (Settings → General)
+  - When enabled, adds the current timestamp to the system prompt
+  - When disabled, omits time information from the prompt
+  - Default: Enabled
+
+- **Include Current Cost** (Settings → General)
+  - When enabled, adds the current task cost to the system prompt
+  - When disabled, omits cost information from the prompt
+  - Default: Enabled
+
+**Example Impact:**
+
+With both enabled, the system prompt includes:
+```
+# Current Time
+Current time in ISO 8601 UTC format: 2025-10-28T23:06:08.458Z
+User time zone: America/Edmonton, UTC-6:00
+
+# Current Cost
+$0.14
+```
+
+With both disabled, these sections are omitted, reducing token usage when you don't need this context.
+
+#### Collapse thinking messages by default
 
 - Location: Settings → UI
 - Default: Enabled (thinking messages are collapsed by default)

docs/providers/gemini.md

@@ -35,6 +35,14 @@ Roo Code supports Google's Gemini family of models through the Google AI Gemini
 
 Roo Code supports the following Gemini models:
 
+### Model Aliases (Recommended)
+
+For stability and automatic updates, use these aliases that point to the latest stable versions:
+
+* `gemini-flash-latest` - Always uses the newest stable Flash model
+* `gemini-pro-latest` - Always uses the newest stable Pro model
+
+
 ### Standard Models
 * `gemini-2.5-flash-preview-05-20`
 * `gemini-2.5-flash-preview-04-17`
@@ -51,6 +59,16 @@ Roo Code supports the following Gemini models:
 * `gemini-1.5-pro-exp-0827`
 * `gemini-exp-1206`
 
+### Preview Models
+
+Preview models include Google's latest experimental features but may change without notice:
+
+* Models with `-preview-` in the name (e.g., `gemini-2.5-flash-preview-05-20`)
+* Models with `-exp-` suffix (e.g., `gemini-2.0-flash-exp`)
+* Models prefixed with `gemini-exp-` (e.g., `gemini-exp-1206`)
+
+Preview models are ideal for testing cutting-edge capabilities but may have breaking changes. Use stable aliases for production work.
+
 ### Thinking Models
 These models require reasoning budget to be enabled in Roo Code settings:
 * `gemini-2.5-flash-preview-05-20:thinking`

docs/update-notes/index.md

@@ -19,6 +19,7 @@ image: /img/social-share.jpg
 
 ### Version 3.29
 
+*   [3.29.3](/update-notes/v3.29.3) (2025-10-28)
 *   [3.29.2](/update-notes/v3.29.2) (2025-10-27)
 *   [3.29.1](/update-notes/v3.29.1) (2025-10-27)
 *   [3.29.0](/update-notes/v3.29.0) (2025-10-24)

docs/update-notes/v3.29.3.mdx

@@ -0,0 +1,33 @@
+---
+description: Adds Roo provider reasoning control, Z.ai Deep Thinking toggle, Gemini model updates, plus fixes for rate limiting, retries, and UI polish.
+keywords:
+  - roo code 3.29.3
+  - release notes
+  - bug fixes
+  - provider updates
+  - qol improvements
+image: /img/social-share.jpg
+---
+
+# Roo Code 3.29.3 Release Notes (2025-10-28)
+
+This patch adds reasoning controls for Roo and Z.ai providers, updates Gemini "latest" models, and delivers stability and UI fixes.
+
+## QOL Improvements
+
+* Toggle time and cost display in the system prompt to reduce model distraction during long runs (thanks jaxnb!) ([#8451](https://github.com/RooCodeInc/Roo-Code/pull/8451))
+* After “Add to Context,” input auto‑focuses and two newlines are inserted for clearer separation, so you can keep typing immediately ([#8877](https://github.com/RooCodeInc/Roo-Code/pull/8877))
+
+## Bug Fixes
+
+* LiteLLM: Prefer max_output_tokens (with fallback to max_tokens) to prevent 400 errors on Claude Sonnet 4.5 via Vertex (thanks fabb!) ([#8455](https://github.com/RooCodeInc/Roo-Code/pull/8455))
+* Messages typed during context condensing now send automatically once condensing finishes; per‑task queues no longer cross‑drain (thanks JosXa!) ([#8478](https://github.com/RooCodeInc/Roo-Code/pull/8478))
+* Rate limiting now uses a monotonic clock and enforces a hard cap at the configured limit to avoid long lockouts (thanks chrarnoldus, intermarkec!) ([#8456](https://github.com/RooCodeInc/Roo-Code/pull/8456))
+* Restore green tests and TypeScript build for LiteLLM after interface changes; keeps monotonic clock fix and token limit behavior ([#8870](https://github.com/RooCodeInc/Roo-Code/pull/8870))
+* Checkpoint menu popover no longer clips long option text; items remain fully visible ([#8867](https://github.com/RooCodeInc/Roo-Code/pull/8867))
+
+## Provider Updates
+
+* Roo provider: Reasoning effort control lets you choose deeper step‑by‑step thinking vs. faster/cheaper responses. See [Roo Code Cloud provider](/providers/roo-code-cloud) for details. ([#8874](https://github.com/RooCodeInc/Roo-Code/pull/8874))
+* Z.ai (GLM‑4.5/4.6): “Enable reasoning” toggle to activate Deep Thinking; hidden on unsupported models (thanks BeWater799!). See [Z.ai provider](/providers/zai). ([#8872](https://github.com/RooCodeInc/Roo-Code/pull/8872))
+* Gemini: Updated model list and “latest” aliases for easier selection (thanks cleacos!). See [Gemini provider](/providers/gemini). ([#8486](https://github.com/RooCodeInc/Roo-Code/pull/8486))

sidebars.ts

@@ -222,6 +222,7 @@ const sidebars: SidebarsConfig = {
           type: 'category',
           label: '3.29',
           items: [
+            { type: 'doc', id: 'update-notes/v3.29.3', label: '3.29.3' },
             { type: 'doc', id: 'update-notes/v3.29.2', label: '3.29.2' },
             { type: 'doc', id: 'update-notes/v3.29.1', label: '3.29.1' },
             { type: 'doc', id: 'update-notes/v3.29.0', label: '3.29.0' },