feat: add inline hero image support to release notes and update content standards

Author: hannesrudolph

.roo/rules-release-notes-writer/1_main_workflow.xml

@@ -445,6 +445,19 @@ Which features should I highlight with expanded sections in the release notes?
             - Otherwise set "image" to /img/social-share.jpg
           </behavior>
         </frontmatter_image>
+        <inline_hero_image>
+          <source>.roo/tmp/release-notes/frontmatter_image_v[version].txt</source>
+          <insertion_point>Immediately after the intro summary sentence below the H1 title</insertion_point>
+          <behavior>
+            - If the persisted path starts with "/img/" and is not "/img/social-share.jpg", insert an HTML image tag under the intro paragraph
+            - Use the exact path value from the source file for src
+            - Follow .roorules Image Tag Format and use width="600"
+            - If the persisted path is "/img/social-share.jpg", skip inline insertion
+          </behavior>
+          <html_snippet><![CDATA[
+<img src="[FRONTMATTER_IMAGE_PATH]" alt="Roo Code v[VERSION] Release" width="600" />
+          ]]></html_snippet>
+        </inline_hero_image>
       </step>
 
       <step number="4">

.roo/rules-release-notes-writer/2_content_standards.xml

@@ -44,6 +44,18 @@ image: /img/social-share.jpg
         <location>Below title</location>
         <example>This release adds context condensing, improves performance, and fixes UI bugs.</example>
       </element>
+
+      <element name="inline_hero_image">
+        <location>Immediately after the intro summary sentence</location>
+        <rules>
+          - Insert only if frontmatter image path resolves to "/img/..." and is not "/img/social-share.jpg"
+          - Use an HTML image tag per site rules with width="600"
+          - Set src from .roo/tmp/release-notes/frontmatter_image_v[version].txt and alt to "Roo Code v[VERSION] Release"
+        </rules>
+        <template><![CDATA[
+<img src="/img/vX.Y.Z/vX.Y.Z.png" alt="Roo Code vX.Y.Z Release" width="600" />
+        ]]></template>
+      </element>
     </required_elements>
   </file_structure>
 

docs/update-notes/v3.28.8.mdx

@@ -13,9 +13,11 @@ image: /img/v3.28.8/v3.28.8.png
 
 This release fixes critical GPT-5-Codex tool usage errors, improves context condensing, and adds new free models to the Roo provider.
 
+<img src="/img/v3.28.8/v3.28.8.png" alt="Roo Code v3.28.8 Release" width="600" />
+
 ## Fixed: GPT-5-Codex errors and more!
 
-We've resolved the situation where LLMs would sometimes not make tool calls in their repsonse which improves Roo's overall flow. ([#8292](https://github.com/RooCodeInc/Roo-Code/pull/8292))
+We've resolved the situation where LLMs would sometimes not make tool calls in their response which improves Roo's overall flow. ([#8292](https://github.com/RooCodeInc/Roo-Code/pull/8292))
 
 - **GPT-5-Codex Response Fix**: Fixes the issue where the model `gpt-5-codex` (and less frequently other models) would send a response with no assistant message
 - **Completion Tool Reliability**: This fix eliminates some situations where the LLM would repeat its last text message when the attempt_completion tool was called
@@ -28,7 +30,7 @@ We've resolved the situation where LLMs would sometimes not make tool calls in t
 
 ## Bug Fixes
 
-* **Context Condensing**: Fixed an issue where the initial task request was being lost during context condensing, causing Roo to try to re-answer the original task ask when resuming after condensing([#8298](https://github.com/RooCodeInc/Roo-Code/pull/8298))
+* **Context Condensing**: Fixed an issue where the initial task request was being lost during context condensing, causing Roo to try to re-answer the original task ask when resuming after condensing ([#8298](https://github.com/RooCodeInc/Roo-Code/pull/8298))
 
 ## Provider Updates
 

docs/update-notes/v3.28.mdx

@@ -93,8 +93,8 @@ This gives teams a higher-capacity OpenAI option without extra configuration.[#8
 
 ## Bug Fixes
 
-* **Fixed "No tool used" Errors**: Resolved the situation where LLMs would sometimes not make tool calls in their repsonse which improves Roo's overall flow. ([#8292](https://github.com/RooCodeInc/Roo-Code/pull/8292))
-* **Context Condensing**: Fixed an issue where the initial task request was being lost during context condensing, causing Roo to try to re-answer the original task ask when resuming after condensing([#8298](https://github.com/RooCodeInc/Roo-Code/pull/8298))
+* **Fixed "No tool used" Errors**: Resolved the situation where LLMs would sometimes not make tool calls in their response which improves Roo's overall flow. ([#8292](https://github.com/RooCodeInc/Roo-Code/pull/8292))
+* **Context Condensing**: Fixed an issue where the initial task request was being lost during context condensing, causing Roo to try to re-answer the original task ask when resuming after condensing ([#8298](https://github.com/RooCodeInc/Roo-Code/pull/8298))
 * **Roo provider stays signed in**: Roo provider tokens refresh automatically and the local evals app binds to port 3446 for predictable scripts (via [#8224](https://github.com/RooCodeInc/Roo-Code/pull/8224))
 * **Checkpoint text stays on one line**: Prevented multi-line wrapping in languages such as Chinese, Korean, Japanese, and Russian so the checkpoint UI stays compact (via [#8207](https://github.com/RooCodeInc/Roo-Code/pull/8207); reported in [#8206](https://github.com/RooCodeInc/Roo-Code/issues/8206))
 * **Ollama respects Modelfile num_ctx**: Roo now defers to your Modelfile’s context window to avoid GPU OOMs while still allowing explicit overrides when needed (via [#7798](https://github.com/RooCodeInc/Roo-Code/pull/7798); reported in [#7797](https://github.com/RooCodeInc/Roo-Code/issues/7797))