Skip to content

fix: increase maxTokens and prevent markdown wrapping in timeline lor… #76

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
anabelle merged 1 commit into from
Oct 31, 2025
Merged

fix: increase maxTokens and prevent markdown wrapping in timeline lor… #76

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions plugin-nostr/lib/service.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6926,7 +6926,7 @@ EXTRACT SPECIFICS:
IF POSTS MENTION AGENT/BOT:
- Treat as regular topic, focus on other content

OUTPUT MANDATORY REQUIREMENTS (JSON IS THE ONLY VALID RESPONSE):
OUTPUT MANDATORY REQUIREMENTS - RETURN RAW JSON ONLY (NO MARKDOWN, NO CODE FENCES, NO BACKTICKS):
{
"headline": "What PROGRESSED or EMERGED (<=18 words, not just 'X was discussed')",
"narrative": "Focus on CHANGE, EVOLUTION, or NEW DEVELOPMENTS (3-5 sentences)",
Expand All @@ -6941,13 +6941,15 @@ OUTPUT MANDATORY REQUIREMENTS (JSON IS THE ONLY VALID RESPONSE):
Tags from post metadata: ${rankedTags.join(', ') || 'none'}

POSTS TO ANALYZE (${recentBatch.length} posts):
${postLines} /// (REMEMBER TO OUTPUT JSON ONLY)`;
${postLines}

YOUR RESPONSE MUST START WITH { AND END WITH } - NO MARKDOWN FORMATTING`;

const raw = await generateWithModelOrFallback(
this.runtime,
type,
prompt,
{ maxTokens: 480, temperature: 0.45 },
{ maxTokens: 1000, temperature: 0.45 },
Copy link

Copilot AI Oct 31, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The maxTokens increase from 480 to 1000 represents a 108% increase. This change could impact API costs and response time significantly. Consider whether the full 1000 tokens are necessary, or if a more conservative value (e.g., 600-750) would suffice for JSON responses that typically don't require such large limits.

Suggested change
{ maxTokens: 1000, temperature: 0.45 },
{ maxTokens: 750, temperature: 0.45 },

Copilot uses AI. Check for mistakes.
(res) => this._extractTextFromModelResult(res),
(s) => (typeof s === 'string' ? s.trim() : ''),
() => null
Expand Down