CSO @ https://teapawt.net/t.co/SLWp7LpcdH | builder / thinker 🤖 #EDCWG @AlzheimerEurope, ex @uni_lu, 2 PhDs (AI / ALIFE), 3 kids, dog person
Graz, Austria
Joined February 2023
- Tweets365
- Following103
- Followers77
- Likes3.7K
Pinned Tweet
🚀 Minor release 1.7.0 of our #Scala client is out!
- Tool loops keep the model's reasoning: @OpenAI, @AnthropicAI, Gemini, Vertex AI, DeepSeek, @MistralAI, MiniMax
- Failover policy: per-try timeouts, deadline, parse retries
- Case-class schemas: Option = required + nullable
Also new: GPT-6.1 Terra, MiniMax-M3.1-Flash, Gemini URL context, Vertex AI global / EU / US endpoints, and the decision models Sarvam Prism + Bespoke Nimble.
Nullable tool parameters need a different schema form per host - we measured 7, the client picks the right one 👇
1
96
Scala 2.12 / 2.13 / 3:
"io.cequence" %% "openai-scala-client" % "1.7.0"
Release notes 👉: github.com/cequence-io/opena…
Changelog: github.com/cequence-io/opena…
Docs: github.com/cequence-io/opena…
14
Sláinte, Dublin! The Irish PM Micheál Martin welcomed us at the #36AEC opening, and the days that followed were moving and inspiring as every year 🧠
Squeezed in a swim in the sea too 🏊♂️
Huge kudos to @AlzheimerEurope and the organizers! #EDCWG
1
2
95
🚀 Version 1.6.0 of our #Scala client is out!
Meta's Muse, Gemini 4 Argon, DeepSeek V4.1 Flash, Jev 1.14, Liquid's d1-ultra, Perplexity's v1.2 deciders... all live-tested 🔥
@typesafeai @liquidai @perplexity_ai @GeminiApp
Release notes in the comments 👇
🖼️ 𝐉𝐞𝐯 𝟏.𝟏𝟒 𝐢𝐧 𝐭𝐲𝐩𝐞𝐬
Images, bounding boxes and 262k-token context from @typesafeai's latest - all of it typed: BoxQuestion in, BoundingBox out.
Finally, a decision model that can point 😉
1
20
Release notes 👉: github.com/cequence-io/opena…
Full changelog: github.com/cequence-io/opena…
1
16
Tested the new long-context decision model on its launch day - 513 questions and 296K tokens in a single call 🔥
Tested ✅ Snap is in our Scala client (ships in 1.6.0): 513 questions in one call in ~1.4 s, where most decision APIs cap at 32-255 🔥 Wishlist: data-URL images, a request-id header, decision-only /v1/models. Max input we hit: 295,957 tokens, not 384K 🤔
github.com/cequence-io/opena…
2
106
🚀 Version 1.5.0 of our #Scala client is out!
Decision models are taking over the world - Jev, d1, Luna, Microsoft-Decision-1, Perplexity's decider... so we put eight hosts behind one interface 🔥
@typesafeai @liquidai @OpenAIDevs @MicrosoftAI
Release notes in the comments 👇
🧩 𝐓𝐲𝐩𝐞𝐝 𝐝𝐞𝐜𝐢𝐬𝐢𝐨𝐧𝐬 & 𝐠𝐮𝐚𝐫𝐝𝐫𝐚𝐢𝐥𝐬
- decide[T]: case class in, case class out, with probabilities
- JSON schema from any case class (Scala 2 & 3), via @JsonSchemaDescription / @JsonSchemaRange
- rerank for RAG
- guardrails with any decision model
Release notes 👉: github.com/cequence-io/opena…
Full changelog: github.com/cequence-io/opena…
Decision models guide: github.com/cequence-io/opena…
56
Two weeks ago in Žilina I spoke at Alzheimer Fórum 2026 about what our European Dementia Carers Working Group at @AlzheimerEurope actually does - from reviewing drug-study materials to lunch debates in the European Parliament 🇪🇺
Huge kudos to the organisers 🙏
#EDCWG #dementia
1
3
129
Happy Oct 1st! We're committed to shipping every 1-2 weeks, so here we are - v1.4.0 of our @OpenAI #Scala client:
- OpenAI Agents API as a chat completion
- Human approval mid-stream
- @liquidai d1 as a 2nd decision model next to #Jev
More on GitHub ⬇️
github.com/cequence-io/opena…
Release notes 👉: github.com/cequence-io/opena…
Full changelog: github.com/cequence-io/opena…
1
78
🚀 @scala_lang devs - 𝐎𝐩𝐞𝐧𝐀𝐈-𝐒𝐜𝐚𝐥𝐚-𝐂𝐥𝐢𝐞𝐧𝐭 𝐯𝟏.𝟑.𝟎 is out! Our biggest release yet - 292 commits, 2 new modules.
@typesafeai #Jev as a drop-in, typed streaming on every provider, batches wherever they exist, one HTTP engine for all.
Here's the rundown 🧵
⚙️ 𝐎𝐧𝐞 𝐇𝐓𝐓𝐏 𝐄𝐧𝐠𝐢𝐧𝐞, 𝐌𝐚𝐧𝐲 𝐏𝐫𝐨𝐯𝐢𝐝𝐞𝐫𝐬
- ws-client 1.0: share one pool and one actor system across all providers via withEngine(engine)
- No Materializer needed anywhere, and the Pekko engine already runs sync calls
1
30
That's it folks! And plenty more didn't fit - @AnthropicAI Managed Agents, Files & Skills, Graders API, GPT-6 Astra, Bedrock, @GeminiApp Batch Mode...
Upgrade today 🥳
Release notes: github.com/cequence-io/opena…
GitHub: github.com/cequence-io/opena…
#Scala #LLM #AI @Cequence_io
2
56