release/1.1.1-alpha #353
Merged
release/1.1.1-alpha #353
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…keywords Updated minimum Rhino version requirement from 8.19 to 8.24 and expanded keywords list to include new AI providers (anthropic, open-router) and split compound keywords for better discoverability.
…eflect unstable development status
…estrict Text2Json to compatible models Added structured-outputs-2025-11-13 beta header support for Anthropic Sonnet 4.5 and Opus 4.1 models with json_schema output_format. Removed Text2Json capability from models that don't support structured outputs. Updated default models to claude-sonnet-4-5 for Text2Json and added Reasoning capability to all Claude 3.x/4.x models. Deprecated claude-3-7-sonnet variants.
…ure by removing redundant wrapper
#351) ## Description This PR aligns the Anthropic and OpenAI provider model registries with the latest available models and capabilities, and adjusts defaults so that AI text / tool / JSON workflows use the most appropriate models. ### Anthropic - Added explicit dated Claude 3.x / 4.x / 4.5 model identifiers (e.g. `claude-haiku-4-20241022`, `claude-sonnet-4-5-20250929`) to the Anthropic provider registry. - Switched the default Anthropic text/tool/json model to `claude-haiku-4-5`. - Marked only Sonnet 4.5 / Opus 4.1 variants as supporting `Text2Json` / structured output, so JSON tools are routed to the correct models. - Kept shorthand model names for backwards compatibility while preferring the dated variants in capability metadata. ### OpenAI - Extended the OpenAI provider model registry to include GPT‑5.1 series and code-focused variants: - `gpt-5.1`, `gpt-5.1-chat-latest` - `gpt-5.1-codex`, `gpt-5.1-codex-mini` - `gpt-5-codex`, `codex-mini-latest` - Tuned `Rank` values so selection logic prefers GPT‑5.1 family for general chat / reasoning, and codex models for code-oriented and tool-heavy workloads. - Kept existing GPT‑4.x and o‑series entries unchanged aside from ranking. ### Mistral - Removed duplicated `mistral-small` model. ## Breaking Changes - No breaking changes to public APIs are expected. - Model selection behavior may change to favor newer, more capable models (Claude 4.5 / GPT‑5.1 / codex variants) when defaults are used, but existing explicit model selections remain valid. ## Testing Done - Built the solution locally. - Confirmed Anthropic default model now resolves to `claude-haiku-4-5`. - Tested list generate with Anthropic successfully returns a json list. ## Checklist - [x] This PR is focused on a single feature or bug fix - [x] Version in Solution.props was updated, if necessary, and follows semantic versioning - [x] CHANGELOG.md has been updated - [x] PR title follows [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/) format - [x] PR description follows [Pull Request Description Template](#pull-request-description-template)
… fixes (#352) This PR prepares the release for version 1.1.1-alpha with version update and code style fixes: - Updated version in Solution.props - Updated changelog with closed-solved issues - Updated README badges
marc-romu
approved these changes
Nov 24, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
SmartHopper 1.1.1-alpha: Provider model updates [Patch]
This patch focuses on AI provider registry and capability alignment, bringing clearer model identifiers and safer defaults across Anthropic and OpenAI.
Detailed list of changes:
Anthropic:
claude-haiku-4-5for faster, cost‑effective defaults.OpenAI: