Merge branch 'main' into i/fix-gemini-sources-as-separate-msg

Author: mrubens

.github/workflows/code-qa.yml

@@ -86,22 +86,38 @@ jobs:
             - name: Create .env.local file
               working-directory: apps/vscode-e2e
               run: echo "OPENROUTER_API_KEY=${{ secrets.OPENROUTER_API_KEY }}" > .env.local
+            - name: Set VS Code test version
+              run: echo "VSCODE_VERSION=1.101.2" >> $GITHUB_ENV
+            - name: Cache VS Code test runtime
+              uses: actions/cache@v4
+              with:
+                  path: apps/vscode-e2e/.vscode-test
+                  key: ${{ runner.os }}-vscode-test-${{ env.VSCODE_VERSION }}
+            - name: Pre-download VS Code test runtime with retry
+              working-directory: apps/vscode-e2e
+              run: |
+                  for attempt in 1 2 3; do
+                    echo "Download attempt $attempt of 3..."
+                    node -e "
+                    const { downloadAndUnzipVSCode } = require('@vscode/test-electron');
+                    downloadAndUnzipVSCode({ version: process.env.VSCODE_VERSION || '1.101.2' })
+                      .then(() => {
+                        console.log('✅ VS Code test runtime downloaded successfully');
+                        process.exit(0);
+                      })
+                      .catch(err => {
+                        console.error('❌ Failed to download VS Code (attempt $attempt):', err);
+                        process.exit(1);
+                      });
+                    " && break || {
+                      if [ $attempt -eq 3 ]; then
+                        echo "All download attempts failed"
+                        exit 1
+                      fi
+                      echo "Retrying in 5 seconds..."
+                      sleep 5
+                    }
+                  done
             - name: Run integration tests
               working-directory: apps/vscode-e2e
               run: xvfb-run -a pnpm test:ci
-
-    notify-slack-on-failure:
-        runs-on: ubuntu-latest
-        needs: [check-translations, knip, compile, unit-test, integration-test]
-        if: ${{ always() && github.event_name == 'push' && github.ref == 'refs/heads/main' && contains(needs.*.result, 'failure') }}
-        steps:
-            - name: Checkout code
-              uses: actions/checkout@v4
-
-            - name: Send Slack notification on failure
-              uses: ./.github/actions/slack-notify
-              with:
-                  webhook-url: ${{ secrets.SLACK_WEBHOOK_URL }}
-                  channel: "#ci"
-                  workflow-name: "Code QA"
-                  failed-jobs: ${{ toJSON(needs) }}

.github/workflows/discord-pr-notify.yml

@@ -29,7 +29,7 @@ argument-hint: patch | minor | major
 6. If the generate_image tool is available, create a release image at `releases/[version]-release.png`
     - The image should feature a realistic-looking kangaroo doing something human-like that relates to the main highlight of the release
     - Pass `releases/template.png` as the reference image for aspect ratio and kangaroo style
-    - Add the generated image to .changeset/v[version].md before the list of changes with format: `![X.Y.Z Release - Description](releases/X.Y.Z-release.png)`
+    - Add the generated image to .changeset/v[version].md before the list of changes with format: `![X.Y.Z Release - Description](/releases/X.Y.Z-release.png)`
 7. If a major or minor release:
     - Ask the user what the three most important areas to highlight are in the release
     - Update the English version relevant announcement files and documentation (webview-ui/src/components/chat/Announcement.tsx, README.md, and the `latestAnnouncementId` in src/core/webview/ClineProvider.ts)

.roo/commands/release.md

@@ -1,16 +1,61 @@
 # Roo Code Changelog
 
+## [3.26.7] - 2025-09-05
+
+![3.26.7 Release - OpenAI Service Tiers](/releases/3.26.7-release.png)
+
+- Feature: Add OpenAI Responses API service tiers (flex/priority) with UI selector and pricing (thanks @hannesrudolph!)
+- Feature: Add DeepInfra as a model provider in Roo Code (#7661 by @Thachnh, PR by @Thachnh)
+- Feature: Update kimi-k2-0905-preview and kimi-k2-turbo-preview models on the Moonshot provider (thanks @CellenLee!)
+- Feature: Add kimi-k2-0905-preview to Groq, Moonshot, and Fireworks (thanks @daniel-lxs and Cline!)
+- Fix: Prevent countdown timer from showing in history for answered follow-up questions (#7624 by @XuyiK, PR by @daniel-lxs)
+- Fix: Moonshot's maximum return token count limited to 1024 issue resolved (#6936 by @greyishsong, PR by @wangxiaolong100)
+- Fix: Add error transform to cryptic OpenAI SDK errors when API key is invalid (#7483 by @A0nameless0man, PR by @app/roomote)
+- Fix: Validate MCP tool exists before execution (#7631 by @R-omk, PR by @app/roomote)
+- Fix: Handle zsh glob qualifiers correctly (thanks @mrubens!)
+- Fix: Handle zsh process substitution correctly (thanks @mrubens!)
+- Fix: Minor zh-TW Traditional Chinese locale typo fix (thanks @PeterDaveHello!)
+
+## [3.26.6] - 2025-09-03
+
+![3.26.6 Release - Bug Fixes and Tool Improvements](/releases/3.26.6-release.png)
+
+- Add experimental run_slash_command tool to let the model initiate slash commands (thanks @app/roomote!)
+- Fix: use askApproval wrapper in insert_content and search_and_replace tools (#7648 by @hannesrudolph, PR by @app/roomote)
+- Add Kimi K2 Turbo model configuration to moonshotModels (thanks @wangxiaolong100!)
+- Fix: preserve scroll position when switching tabs in settings (thanks @DC-Dancao!)
+
+## [3.26.5] - 2025-09-03
+
+![3.26.5 Release - Enhanced AI Thinking Capabilities](/releases/3.26.5-release.png)
+
+- feat: Add support for Qwen3 235B A22B Thinking 2507 model in chutes (thanks @mohammad154!)
+- feat: Add auto-approve support for MCP access_resource tool (#7565 by @m-ibm, PR by @daniel-lxs)
+- feat: Add configurable embedding batch size for code indexing (#7356 by @BenLampson, PR by @app/roomote)
+- fix: Add cache reporting support for OpenAI-Native provider (thanks @hannesrudolph!)
+- feat: Move message queue to the extension host for better performance (thanks @cte!)
+
+## [3.26.4] - 2025-09-01
+
+![3.26.4 Release - Memory Optimization](/releases/3.26.4-release.png)
+
+- Optimize memory usage for image handling in webview (thanks @daniel-lxs!)
+- Fix: Special tokens should not break task processing (#7539 by @pwilkin, PR by @pwilkin)
+- Add Ollama API key support for Turbo mode (#7147 by @LivioGama, PR by @app/roomote)
+- Rename Account tab to Cloud tab for clarity (thanks @app/roomote!)
+- Add kangaroo-themed release image generation (thanks @mrubens!)
+
 ## [3.26.3] - 2025-08-29
 
-![3.26.3 Release - Kangaroo Photo Editor](releases/3.26.3-release.png)
+![3.26.3 Release - Kangaroo Photo Editor](/releases/3.26.3-release.png)
 
 - Add optional input image parameter to image generation tool (thanks @roomote!)
 - Refactor: Flatten image generation settings structure (thanks @daniel-lxs!)
 - Show console logging in vitests when the --no-silent flag is set (thanks @hassoncs!)
 
 ## [3.26.2] - 2025-08-28
 
-![3.26.2 Release - Kangaroo Digital Artist](releases/3.26.2-release.png)
+![3.26.2 Release - Kangaroo Digital Artist](/releases/3.26.2-release.png)
 
 - feat: Add experimental image generation tool with OpenRouter integration (thanks @daniel-lxs!)
 - Fix: Resolve GPT-5 Responses API issues with condensing and image support (#7334 by @nlbuescher, PR by @daniel-lxs)
@@ -19,7 +64,7 @@
 
 ## [3.26.1] - 2025-08-27
 
-![3.26.1 Release - Kangaroo Network Engineer](releases/3.26.1-release.png)
+![3.26.1 Release - Kangaroo Network Engineer](/releases/3.26.1-release.png)
 
 - Add Vercel AI Gateway provider integration (thanks @joshualipman123!)
 - Add support for Vercel embeddings (thanks @mrubens!)
@@ -31,7 +76,7 @@
 
 ## [3.26.0] - 2025-08-26
 
-![3.26.0 Release - Kangaroo Speed Racer](releases/3.26.0-release.png)
+![3.26.0 Release - Kangaroo Speed Racer](/releases/3.26.0-release.png)
 
 - Sonic -> Grok Code Fast
 - feat: Add Qwen Code CLI API Support with OAuth Authentication (thanks @evinelias and Cline!)