Conversation
|
Caution Review failedThe pull request is closed. WalkthroughThe system prompt text was updated in both the configuration file and the deployment template to include explicit instructions for memory and context retention. The new prompt directs the assistant to remember provided parameters and reuse them in subsequent conversation turns, illustrated with an expanded example. No code or exported entities were changed. Changes
Possibly related PRs
📜 Recent review detailsConfiguration used: CodeRabbit UI 📒 Files selected for processing (2)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (2)
config/systemprompt.txt (1)
6-18: Synchronise terminology and tighten wording in the worked example.
cluster IDis introduced, then the list at line 15 jumps to “nodes” without re-affirming the retained parameter. Recommend a short recap (“…for cluster ‘ocp-prod-123’ …”) in the final user request to keep the thread crystal-clear for downstream LLMs that may be sensitive to subtle context gaps.template.yaml (1)
127-145: Terminology drift between prompt copies (“cluster name” vs “project name”).
This version lists “project name”, whileconfig/systemprompt.txtlists “cluster name”. Divergence invites confusion and future drift; consider DRYing the prompt into a single source (e.g., include the file via ConfigMap) and ensure the parameter list is identical.
| **Memory and Context Retention:** | ||
| You are designed to retain and utilize information from the ongoing conversation. Once a parameter value (e.g., cluster ID, cluster name, resource type) has been provided by the user or identified through a tool's output, you **MUST** store it in your internal memory and use it for subsequent relevant queries within the same conversation. **Do not ask for information you already possess in your memory.** |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Clarify scope & privacy of “internal memory”.
The prompt mandates that the assistant persist parameters but doesn’t specify that this memory is strictly per-conversation and must not be carried across sessions or leaked back to the user. Explicitly limiting the retention scope guards against privacy / PII leakage and aligns with typical compliance requirements.
🤖 Prompt for AI Agents
In config/systemprompt.txt around lines 3 to 4, clarify that the assistant's
internal memory for storing parameters is strictly limited to the current
conversation session only and must not persist across sessions or be exposed to
the user. Update the prompt text to explicitly state this scope and privacy
constraint to prevent any unintended data leakage or privacy issues.
Enhance agent memory and context awareness Instructs the AI agent to remember previously provided information to avoid redundant prompts. Signed-off-by: Eran Cohen <eranco@redhat.com>
|
Closing in favor of: #38 |
1 participant
Enhance agent memory and context awareness
Instructs the AI agent to remember previously provided information to avoid redundant prompts.
Summary by CodeRabbit