harald/zeroclaw
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

fix(channel): replace hardcoded Discord bot text with generic channel text

Browse source 
The Channel Capabilities section in build_system_prompt() was hardcoded
to say "You are running as a Discord bot" for ALL channels, including
Telegram. This caused the LLM to misidentify itself and reference
Discord-specific features regardless of the actual channel.

Replace with generic "messaging bot" text. Per-channel delivery
instructions already exist via channel_delivery_instructions().

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Edvard 2026-02-19 16:07:25 -05:00 • committed by Chummy
parent e0ca73336a
commit 3a8a1754ef
1 changed files with 3 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

9
src/channels/mod.rs
View file

@ -1357,10 +1357,7 @@ pub fn build_system_prompt(
// ── 8. Channel Capabilities ───────────────────────────────────── // ── 8. Channel Capabilities ─────────────────────────────────────
prompt.push_str("## Channel Capabilities\n\n"); prompt.push_str("## Channel Capabilities\n\n");
prompt.push_str( prompt.push_str("- You are running as a messaging bot. Your response is automatically sent back to the user's channel.\n");
"- You are running as a Discord bot. You CAN and do send messages to Discord channels.\n",
);
prompt.push_str("- When someone messages you on Discord, your response is automatically sent back to Discord.\n");
prompt.push_str("- You do NOT need to ask permission to respond — just respond directly.\n"); prompt.push_str("- You do NOT need to ask permission to respond — just respond directly.\n");
prompt.push_str("- NEVER repeat, describe, or echo credentials, tokens, API keys, or secrets in your responses.\n"); prompt.push_str("- NEVER repeat, describe, or echo credentials, tokens, API keys, or secrets in your responses.\n");
prompt.push_str("- If a tool output contains credentials, they have already been redacted — do not mention them.\n\n"); prompt.push_str("- If a tool output contains credentials, they have already been redacted — do not mention them.\n\n");
@ -3785,8 +3782,8 @@ mod tests {
"missing Channel Capabilities section" "missing Channel Capabilities section"
); );
assert!( assert!(
prompt.contains("running as a Discord bot"), prompt.contains("running as a messaging bot"),
"missing Discord context" "missing channel context"
); );
assert!( assert!(
prompt.contains("NEVER repeat, describe, or echo credentials"), prompt.contains("NEVER repeat, describe, or echo credentials"),