diff --git a/server/prompts/commentary_system.txt b/server/prompts/commentary_system.txt
index 58d51ef0..e173b338 100644
--- a/server/prompts/commentary_system.txt
+++ b/server/prompts/commentary_system.txt
@@ -63,10 +63,10 @@ When to skip:
 
 Freshness and anti-repeat:
 - Check prior assistant messages in the timeline before speaking.
-- Do not send back-to-back lines to the same user about the same rover unless there is a clear new trigger (new EVENT, direct question, or sharp chat shift).
+- Do not send back-to-back lines to the same user about the same rover.
 - If your planned line could be swapped with your previous line by only changing a name, output SKIP.
 - Do not reuse the same opener pattern twice in a row.
-- If the last assistant line already covered that person+rover context and no meaningful new signal exists, output SKIP.
+- If the last assistant line already covered that person+rover context, output SKIP.
 
 Grounding:
 - Use timeline for flow.
diff --git a/server/src/rewards/definitions/discordStalkerPing.js b/server/src/rewards/definitions/discordStalkerPing.js
index 14afd098..bc5c12ef 100644
--- a/server/src/rewards/definitions/discordStalkerPing.js
+++ b/server/src/rewards/definitions/discordStalkerPing.js
@@ -1,7 +1,7 @@
 module.exports = {
   id: 'discordStalkerPing',
-  name: 'Stalker Ping',
-  goal: 800,
+  name: 'Discord Ping',
+  goal: 500,
   async run(ctx) {
     ctx.publishEvent({
       source: 'buttonBoxReward',
diff --git a/server/src/services/llmCommentaryService.js b/server/src/services/llmCommentaryService.js
index 10e19e01..6973d54d 100644
--- a/server/src/services/llmCommentaryService.js
+++ b/server/src/services/llmCommentaryService.js
@@ -22,7 +22,7 @@ const ACTIVITY_WINDOW_MS = 60000;
 const ACTIVITY_BUCKET_MS = 1000;
 const ACTIVITY_SCORE_WINDOW_MS = 30000;
 const SELF_TALK_WINDOW_MS = 30 * 60 * 1000;
-const MAX_CONTEXT_EVENTS = 6;
+const MAX_CONTEXT_EVENTS = 15;
 const MAX_RUN_HISTORY = 30;
 const MAX_ROVER_EVENTS = 400;
 const POST_COOLDOWN_MS = 10000;