Zum Hauptinhalt springen
IT Security NachrichtenMaking HTTP header injection critical with one prompt(04.11.2026 um 16:12 Uhr)
••
IT Security NachrichtenHackers Exploit Node-RED Flaw to Deploy Malicious Flows(04.11.2026 um 15:35 Uhr)
•
AI & KI NachrichtenOpenAI Expands Security Testing: Bug Bounties Near $172,000(04.11.2026 um 15:55 Uhr)
•
IT Security NachrichtenOne Hacker Used 12 AI Agents to Target Taiwan's Emergency Services(04.11.2026 um 16:41 Uhr)
•
IT Security NachrichtenRussian hackers use breached sites to steal iPhone and Android data(04.11.2026 um 16:58 Uhr)
•
IT Security Nachrichten7 Best Security Add-Ons for Microsoft Entra in 2026(04.11.2026 um 15:51 Uhr)
••••
IT Security NachrichtenMaking HTTP header injection critical with one prompt(04.11.2026 um 16:12 Uhr)
••
IT Security NachrichtenHackers Exploit Node-RED Flaw to Deploy Malicious Flows(04.11.2026 um 15:35 Uhr)
•
AI & KI NachrichtenOpenAI Expands Security Testing: Bug Bounties Near $172,000(04.11.2026 um 15:55 Uhr)
•
IT Security NachrichtenOne Hacker Used 12 AI Agents to Target Taiwan's Emergency Services(04.11.2026 um 16:41 Uhr)
•
IT Security NachrichtenRussian hackers use breached sites to steal iPhone and Android data(04.11.2026 um 16:58 Uhr)
•
IT Security Nachrichten7 Best Security Add-Ons for Microsoft Entra in 2026(04.11.2026 um 15:51 Uhr)
••••
Intelligence View
⚡ tsecurity.de Intelligence

GitHub Release: cline/cline vsdk/sdk/v0.0.91 (07.10.2026)

Release sdk/sdk/v0.0.91 von cline/cline auf GitHub: Responses that end with a missing or unrecognized finish reason are no longer treated as successful…

Beitrag
0
Seite
0
↗ Quelle (GitHub · cline/cline)
Social ReaktionenReagiere als Erste:r — dein Feedback zählt!
cline/clinevsdk/sdk/v0.0.9107.10.2026@github-actions[bot]

  • Responses that end with a missing or unrecognized finish reason are no longer treated as successful completions. AgentModelFinishReason gains unknown (the AI SDK adapter maps unified other and missing reasons to it instead of stop). Without tool activity, the agent keeps the partial response and continues once with a hidden user message; a second unknown finish fails the run. Queued user messages are now consumed at every request boundary, including the first iteration

  • Stdio MCP servers get a 10s default initialize budget (was 3s). npx/uvx launchers through cmd.exe on Windows routinely took 3-6s and were silently dropped from the session. An explicit timeout still overrides it

  • The Anthropic provider sends the server-side refusal fallbacks option only to api.anthropic.com. Custom endpoints such as Azure AI Foundry rejected it with a 400. New isOfficialAnthropicEndpoint helper

  • The portable reasoning level for the cline and openai-compatible adapters snaps to the model's advertised effort levels. Kimi K3 (low/high/max) was sent medium and minimal, which it rejects

  • OpenAI-compatible providers (generic, vercel-ai-gateway, user-defined ids) write providerOptions under the camelCase alias only, which stops the per-chunk providerOptions key 'openai-compatible' deprecation warning from @ai-sdk/openai-compatible

  • New apiKeyOptional provider fact (GatewayProviderMetadata.apiKeyOptional, resolveProviderApiKeyOptional, ProviderListItem.auth.apiKeyOptional), declared on openai-compatible, ollama, lmstudio, litellm, vertex, bedrock, and user-added endpoints from providers.json/models.json

  • Rules: new listEnabledRulesFromRecords / loadRulesForSystemPromptFromRecords exports. The combined user-instruction service now orders rules by name, matching the single-workspace path

  • Opt-in Langfuse tracing for BYOK providers (CLINE_LANGFUSE_ALL_PROVIDERS), plus operator tags, metadata and environment via CLINE_LANGFUSE_TAGS, CLINE_LANGFUSE_METADATA, LANGFUSE_TRACING_ENVIRONMENT

  • Hook discovery telemetry handles Windows path separators

  • Refreshed the model catalog. The Cline free list adds Solar Mini 4 and drops DeepSeek V4.1 Flash and space-bunny-alpha. Adds the Engy provider. Default models change for AKI.IO, Blue Claw, CoralBricks, CrossModel (GPT-6.1 Sol), DevPass, LLM Gateway, Mistral, NanoGPT, Requesty (Mistral Large 4), Neon (Claude Opus 5.5), Subconscious, and The Grid AI


Full Changelog: sdk/sdk/v0.0.90...sdk/sdk/v0.0.91

Intelligence Digest gratis Dagelijks het belangrijkste beveiligingsnieuws · kan op elk moment worden opgehaald
Community Rating & Social Proof
⭐ Leser-Wertung
–
Ø / 5.0
Nog geen recensies van lezers
Was deze pagina nuttig?
0
Jetzt Bewertung abgeben
🟢 Niedrig (1-3.9) 🟡 Mittel (4.0-6.9) 🔴 Hoch (7.0-8.9) Kritisch (9.0-10.0)

Verwant Story Cluster & Sources (vector AI)

Trek om te vernieuwen
Nächster Beitrag