Zum Hauptinhalt springen
YouTube Security VideosHow LS Digital troubleshoots Google Ads 10x faster with Ask Advisor(23.10.2026 um 16:43 Uhr)
•
YouTube Security VideosCOMPUTER BILD: Nintendo Switch Sports Resort - Runter vom Sofa!(23.10.2026 um 16:02 Uhr)
•
Sichere ProgrammierungfreeCodeCamp.org: Gemini 4 Argon API Crash Course(23.10.2026 um 16:10 Uhr)
•••
Windows ServerBMW aktualisiert High-Performance Computing - silicon.de(23.10.2026 um 12:15 Uhr)
•••••
YouTube Security VideosHow LS Digital troubleshoots Google Ads 10x faster with Ask Advisor(23.10.2026 um 16:43 Uhr)
•
YouTube Security VideosCOMPUTER BILD: Nintendo Switch Sports Resort - Runter vom Sofa!(23.10.2026 um 16:02 Uhr)
•
Sichere ProgrammierungfreeCodeCamp.org: Gemini 4 Argon API Crash Course(23.10.2026 um 16:10 Uhr)
•••
Windows ServerBMW aktualisiert High-Performance Computing - silicon.de(23.10.2026 um 12:15 Uhr)
•••••
Intelligence View
⚡ tsecurity.de Intelligence

GitHub Release: can1357/oh-my-pi v18.3.4 (27.09.2026)

Release v18.3.4 von can1357/oh-my-pi auf GitHub: @oh-my-pi/pi-ai Fixed Fixed Anthropic OAuth requests capping output at 64k tokens; they now request the…

Beitrag
0
Seite
0
↗ Quelle (GitHub · can1357/oh-my-pi)
Social ReaktionenReagiere als Erste:r — dein Feedback zählt!
can1357/oh-my-piv18.3.427.09.2026@github-actions[bot]

@oh-my-pi/pi-ai


Fixed



  • Fixed Anthropic OAuth requests capping output at 64k tokens; they now request the model's full ceiling (128k on Opus 5.5), matching Claude Code and API-key requests


@oh-my-pi/pi-coding-agent


Breaking Changes



  • Replaced the task tool's complexity field with solutionSpace, a description of how open-ended the subtask is; auto thinking for spawned subagents now picks effort from it alone


Changed



  • auto thinking now picks effort for every turn by how open-ended the problem is, so large volumes of mechanical work no longer raise it


Fixed



  • Fixed agents looping for hours when every turn spends the whole output limit on reasoning: length-stop retries now tell the model its reasoning was discarded and to act in smaller steps, and a subagent whose length-stop recovery gives up now fails with that error instead of being re-prompted into the same loop

  • Fixed tagging a model with ^ mid-session dropping the provider prompt cache for every following turn: new m<N> pseudonyms now arrive as a hidden session notice instead of rewriting the task description, which only absorbs them at a base-prompt rebuild


@oh-my-pi/pi-natives


Fixed



  • Fixed the native addon keeping every bun test --isolate/--parallel test file's global object and module graph alive, which grew each test worker by ~15 MB per file until the run was OOM-killed.


Full Changelog: v18.3.3...v18.3.4

Intelligence Digest — kostenlos Täglich die wichtigsten Security-News · jederzeit abbestellbar
Community Rating & Social Proof
⭐ Leser-Wertung
–
Ø / 5.0
Noch keine Leser-Bewertungen
War diese Seite hilfreich?
0
Jetzt Bewertung abgeben
🟢 Niedrig (1-3.9) 🟡 Mittel (4.0-6.9) 🔴 Hoch (7.0-8.9) Kritisch (9.0-10.0)

Verwandte Story-Cluster & Quellen (Vektor-KI)

Zum Aktualisieren ziehen
Nächster Beitrag