Release v3.29.5

[3.29.5] - 2025-11-01

• Fix: Resolve Qdrant codebase_search error by adding keyword index for type field (#8963 by @rossdonald, PR by @app/roomote)
• Fix cost and token tracking between provider styles to ensure accurate usage metrics (thanks @mrubens!)

Release v3.29.4

[3.29.4] - 2025-10-30

• Feat: Add Minimax Provider (thanks @Maosghoul!)
• Fix: prevent infinite loop when canceling during auto-retry (#8901 by @mini2s, PR by @app/roomote)
• Fix: Enhanced codebase index recovery and reuse ('Start Indexing' button now reuses existing Qdrant index) (#8129 by @jaroslaw-weber, PR by @heyseth)
• Fix: make code index initialization non-blocking at activation (#8777 by @cjlawson02, PR by @daniel-lxs)
• Fix: remove search_and_replace tool from codebase (#8891 by @hannesrudolph, PR by @app/roomote)
• Fix: custom modes under custom path not showing (#8122 by @hannesrudolph, PR by @elianiva)
• Fix: prevent MCP server restart when toggling tool permissions (#8231 by @hannesrudolph, PR by @heyseth)
• Fix: truncate type definition to match max read line (#8149 by @chenxluo, PR by @elianiva)
• Fix: auto-sync enableReasoningEffort with reasoning dropdown selection (thanks @daniel-lxs!)
• Fix: Gate auth-driven Roo model refresh to active provider only (thanks @daniel-lxs!)
• Prevent a noisy cloud agent exception (thanks @cte!)
• Feat: improve @ file search for large projects (#5721 by @Naituw, PR by @daniel-lxs)
• Feat: add zai-glm-4.6 model to Cerebras and set gpt-oss-120b as default (thanks @kevint-cerebras!)
• Feat: rename MCP Errors tab to Logs for mixed-level messages (#8893 by @hannesrudolph, PR by @app/roomote)
• docs(vscode-lm): clarify VS Code LM API integration warning (thanks @hannesrudolph!)

Release v3.29.3

[3.29.3] - 2025-10-28

• Update Gemini models with latest 09-2025 versions including Gemini 2.5 Pro and Flash (#8485 by @cleacos, PR by @roomote)
• Add reasoning support for Z.ai GLM binary thinking mode (#8465 by @BeWater799, PR by @daniel-lxs)
• Enable reasoning in Roo provider (thanks @mrubens!)
• Add settings to configure time and cost display in system prompt (#8450 by @jaxnb, PR by @roomote)
• Fix: Use max_output_tokens when available in LiteLLM fetcher (#8454 by @fabb, PR by @roomote)
• Fix: Process queued messages after context condensing completes (#8477 by @JosXa, PR by @roomote)
• Fix: Use monotonic clock for rate limiting to prevent timing issues (#7770 by @intermarkec, PR by @chrarnoldus)
• Fix: Resolve checkpoint menu popover overflow (thanks @daniel-lxs!)
• Fix: LiteLLM test failures after merge (thanks @daniel-lxs!)
• Improve UX: Focus textbox and add newlines after adding to context (thanks @mrubens!)

Release v3.29.2

[3.29.2] - 2025-10-27

• Add support for LongCat-Flash-Thinking-FP8 models in Chutes AI provider (#8425 by @leakless21, PR by @roomote)
• Fix: Remove specific Claude model version from settings descriptions to avoid outdated references (#8435 by @rwydaegh, PR by @roomote)
• Fix: Correct caching logic in Roo provider to improve performance (thanks @mrubens!)
• Fix: Ensure free models don't display pricing information in the UI (thanks @mrubens!)

Release v3.29.1

[3.29.1] - 2025-10-26

• Fix: Clean up max output token calculations to prevent context window overruns (#8821 by @enerage, PR by @roomote)
• Fix: Change Add to Context keybinding to avoid Redo conflict (#8652 by @swythan, PR by @roomote)
• Fix provider model loading race conditions (thanks @mrubens!)

Release v3.29.0

[3.29.0] - 2025-10-24

• Add token-budget based file reading with intelligent preview to avoid context overruns (thanks @daniel-lxs!)
• Enable browser-use tool for all image-capable models (#8116 by @hannesrudolph, PR by @app/roomote!)
• Add dynamic model loading for Roo Code Cloud provider (thanks @app/roomote!)
• Fix: Respect nested .gitignore files in search_files (#7921 by @hannesrudolph, PR by @daniel-lxs)
• Fix: Preserve trailing newlines in stripLineNumbers for apply_diff (#8020 by @liyi3c, PR by @app/roomote)
• Fix: Exclude max tokens field for models that don't support it in export (#7944 by @hannesrudolph, PR by @elianiva)
• Retry API requests on stream failures instead of aborting task (thanks @daniel-lxs!)
• Improve auto-approve button responsiveness (thanks @daniel-lxs!)
• Add checkpoint initialization timeout settings and fix checkpoint timeout warnings (#7843 by @NaccOll, PR by @NaccOll)
• Always show checkpoint restore options regardless of change detection (thanks @daniel-lxs!)
• Improve checkpoint menu translations (thanks @daniel-lxs!)
• Add GLM-4.6-turbo model to chutes ai provider (thanks @mohammad154!)
• Add Claude Haiku 4.5 to prompt caching models (thanks @hannesrudolph!)
• Expand Z.ai model coverage with GLM-4.5-X, AirX, Flash (thanks @hannesrudolph!)
• Update Mistral Medium model name (#8362 by @ThomsenDrake, PR by @ThomsenDrake)
• Remove GPT-5 instructions/reasoning_summary from UI message metadata to prevent ui_messages.json bloat (thanks @hannesrudolph!)
• Normalize docs-extractor audience tags; remove admin/stakeholder; strip tool invocations (thanks @hannesrudolph!)
• Update X/Twitter username from roo_code to roocode (thanks @app/roomote!)
• Update Configuring Profiles video link (thanks @app/roomote!)
• Fix link text for Roomote Control in README (thanks @laz-001!)
• Remove verbose error for cloud agents (thanks @cte!)
• Try 5s status mutation timeout (thanks @cte!)

Release v3.28.18

[3.28.18] - 2025-10-17

• Fix: Remove request content from UI messages to improve performance and reduce clutter (#5601 by @MuriloFP, #8594 by @multivac2x, #8690 by @hannesrudolph, PR by @mrubens)
• Fix: Prevent file editing issues when git diff views are open (thanks @hassoncs!)
• Fix: Add userAgent to Bedrock client for version tracking (#8660 by @ajjuaire, PR by @app/roomote)
• Feat: Z AI now uses only two coding endpoints for better performance (#8687 by @hannesrudolph)
• Feat: Update image generation model selection for improved quality (thanks @chrarnoldus!)

Release v3.28.17

[3.28.17] - 2025-10-15

• Add support for Claude Haiku 4.5 model (thanks @daniel-lxs!)
• Fix: Update zh-TW run command title translation (thanks @PeterDaveHello!)

Release v3.28.16

[3.28.16] - 2025-10-09

• feat: Add Claude Sonnet 4.5 1M context window support for Claude Code (thanks @ColbySerpa!)
• feat: Identify cloud tasks in the extension bridge (thanks @cte!)
• fix: Add the parent task ID in telemetry (thanks @mrubens!)

Release v3.28.15

[3.28.15] - 2025-10-03

• Add new DeepSeek and GLM models with detailed descriptions to the Chutes provider (thanks @mohammad154!)
• Fix: properly reset cost limit tracking when user clicks "Reset and Continue" (#6889 by @alecoot, PR by app/roomote)
• Fix: improve save button activation in prompts settings (#5780 by @beccare, PR by app/roomote)
• Fix: overeager 'there are unsaved changes' dialog in settings (thanks @brunobergher!)
• Fix: show send button when only images are selected in chat textarea (thanks app/roomote!)
• Fix: Claude Sonnet 4.5 compatibility improvements (thanks @mrubens!)
• Add UsageStats schema and type for better analytics tracking (thanks app/roomote!)
• Include reasoning messages in cloud tasks (thanks @mrubens!)
• Security: update dependency vite to v6.3.6 (thanks app/renovate!)
• Deprecate free grok 4 fast model (thanks @mrubens!)
• Remove unsupported Gemini 2.5 Flash Image Preview free model (thanks @SannidhyaSah!)
• Add structured data to the homepage for better SEO (thanks @mrubens!)
• Update dependency glob to v11.0.3 (thanks app/renovate!)