update prompt (#77)

<!-- This is an auto-generated comment: release notes by openai -->
### Summary by OpenAI

Documentation: This pull request updates the prompt message and default
value of `max_files` input in `action.yml`, adds a note about review
comments in pull requests to `README.md`, and clarifies how to interact
with the bot in the tips section of `src/review.ts`. These changes aim
to improve the user experience and provide better guidance on how to use
the bot effectively.
<!-- end of auto-generated comment: release notes by openai -->

Author: harjotgill

README.md

@@ -74,6 +74,9 @@ Example:
 
 > @openai Can you please review this block of code?
 
+Note: A review comment is a comment made on a diff or a file in the pull
+request.
+
 ### Screenshots
 
 ![PR Summary](./docs/images/openai-pr-summary.png)

action.yml

@@ -12,7 +12,7 @@ inputs:
   max_files:
     required: false
     description: 'Max files to review. Less than or equal to 0 means no limit.'
-    default: '60'
+    default: '50'
   review_comment_lgtm:
     required: false
     description: 'Leave comments even if the patch is LGTM'
@@ -189,7 +189,7 @@ inputs:
     default: |
       Next, I will send you a series of patches. Each patch consists of a diff snippet, 
       and your task is to review every patch. Identify any bug risks or provide 
-      improvement suggestions. If the patch looks good and acceptable, please reply 
+      improvement suggestions. Otherwise, if the patch is acceptable, please reply 
       "LGTM!" with a short comment. 
 
       Your responses will be recorded as review comments on the pull request. 

dist/index.js

@@ -227,8 +227,9 @@ ${filename}: ${summary}
 ---
 
 Tips: 
-- Reply on the review comment left by this bot to ask follow-up questions.
-- Invite the bot into a review conversation by typing \`@openai\` in the beginning of the comment.
+- Reply on review comments left by this bot to ask follow-up questions. 
+  A review comment is a comment on a diff or a file.
+- Invite the bot into a review comment chain by tagging \`@openai\` in a reply.
 `
 
       next_summarize_ids = summarize_final_response_ids