Zum Hauptinhalt springen
Intelligence View
⚡ tsecurity.de Intelligence

GitHub Release: anomalyco/opencode v2.3.2 (18.11.2026)

Release v2.3.2 von anomalyco/opencode auf GitHub: Highlights GPT-6.2 Prompt Caching: GPT-6.2 models don't cache a system prompt sent in the Responses…

Beitrag
0
Seite
0
↗ Quelle (GitHub · anomalyco/opencode)
Cloud & Tech-Stack · 1 Min. Lesezeit
Quelle: GitHub · anomalyco/opencode (github.com)
Rubrik: AI & KI Nachrichten
anomalyco/opencodev2.3.218.11.2026@github-actions[bot]

Highlights



  • GPT-6.2 Prompt Caching: GPT-6.2 models don't cache a system prompt sent in the Responses instructions field, so every step re-billed it as uncached input. OpenCode now sends it as a leading developer message on every Responses route, including OpenAI (API key and ChatGPT sign-in), GitHub Copilot, Zen, Azure and OpenRouter, so it is cached from the second step on. (#64542, #64544)


Core


Bug fixes



  • Fixed GPT-6.2 models re-billing the system prompt as uncached input on every step. On GitHub Copilot gpt-6.2-sol, uncached input per step dropped from about 14,000 tokens to 3. Compaction through /responses/compact now reads the same cached prefix. (#64542, #64544)

  • webfetch structured output no longer repeats the url and format it was called with. (#64534)

Social ReaktionenReagiere als Erste:r — dein Feedback zählt!
Security Briefing Gratis · 1-klik uitschrijven

Intelligence Digest gratis

Dagelijks het belangrijkste beveiligingsnieuws · kan op elk moment worden opgehaald

Community Rating & Social Proof
⭐ Lezersbeoordeling
–
Ø / 5.0
Nog geen recensies van lezers
Was dit artikel nuttig?
0
Geef uw beoordeling
Detailbeoordeling (optioneel)
Inhoud & Kwaliteit
Bron & Geloofwaardigheid
Actualiteit

Verwant Story Cluster & Sources (vector AI)

Trek om te vernieuwen
Widgets & Themen
Widgets werden geladen…
Nächster Beitrag