build(deps-dev): Update langchain-ollama requirement from <1,>=0.3.0 to >=0.3.0,<2#7
Open
dependabot[bot] wants to merge 44 commits into
Open
build(deps-dev): Update langchain-ollama requirement from <1,>=0.3.0 to >=0.3.0,<2#7dependabot[bot] wants to merge 44 commits into
dependabot[bot] wants to merge 44 commits into
Conversation
Added funny GitHub badges
- Fix requirements; - Rename param auth_data to api_key;
- Refactor config-flow to support multiple LLM engines - Added YandexGPT and OpenAI - Basic support for models parameters - Correct README
Add support for multiple LLM engines
Bump version to 0.1.2
Bump version to 0.1.2
- Rollback from community to official gigachain library
Add support for completion models configuration
Bump version
- Add support for choosing models; - Support max_tokens; - Add ability to skip auth validation (for testing purposes); - Added EN readme
Add support for choosing models
Enhance github actions files
* Support inbuilt functionality for controlling home-assistant Inherited from default-agent * Add ability to switch off chat history * Add back HACS Actions
default conversation agent instantiation method was changed
* rc-0.1.8 fix version conflict resolve versions conflict * rc-0.1.8 remove anyscale remove anyscale support
- Migrate from AbstractConversationAgent to ConversationEntity with _async_handle_message(user_input, chat_log) and ChatLog/AssistantContent API - Add conversation.py with GigaChainConversationEntity - Simplify __init__.py to use async_forward_entry_setups/async_unload_platforms - Add 20 tests (11 config flow + 9 conversation entity) with pytest-homeassistant-custom-component - Add CHANGELOG.md based on git commit history - Add full technical documentation (docs/DOCUMENTATION.md) - Fix blocking LLM call, memory leak, deprecated APIs, Anyscale removal - Update to HA best practices: entry.runtime_data, ConfigFlowResult, @callback - Update models (GigaChat-Max, gpt-4o), add verify_ssl option - Add MIT LICENSE, pytest.ini, pre-commit ruff v0.9.7 - Update GitHub Actions to v4/v5, Python 3.12, ruff lint - Remove dead code: Anyscale, test-model.py, duplicate workflows - Version bump to 0.3.0 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
…penai, pytest в CI - Удалён OrderedDict, история управляется нативным ChatLog HA - _chatlog_to_langchain() для конвертации ChatLog ↔ LangChain messages - GigaChat из langchain_gigachat, ChatOpenAI из langchain_openai - Зависимости: langchain-gigachat>=0.3.0, langchain-openai>=0.3.0, langchain-community>=0.4.0 - Шаг pytest в push.yml и pull.yml - 4 новых теста setup/unload (test_setup.py) - Обновлены тесты conversation entity для ChatLog - Итого: 26 тестов (11 config flow + 11 conversation + 4 setup) - Обновлена документация для v0.4.0 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
- _attr_supports_streaming = True для потоковой генерации - client.invoke() через executor заменён на client.astream() (async) - _async_langchain_stream() конвертирует AIMessageChunk → HA delta dicts - async_add_assistant_content_without_tools заменён на async_add_delta_content_stream - 3 новых теста (streaming attr, stream conversion, empty chunks) - Итого: 29 тестов (11 config flow + 14 conversation + 4 setup) - Версия: 0.5.0 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
Complete project rename to reflect multi-provider LLM support: - Domain: gigachain -> smartchain - Entity: GigaChainConversationEntity -> SmartChainConversationEntity - New GitHub repo: ha-smartchain - Updated all imports, translations, manifests, tests Added AI Task entity (SmartChainAITaskEntity): - Implements ai_task.AITaskEntity with _async_generate_data() - Supports structured output (JSON parsing) - Reuses conversation entity's LangChain streaming + tool calling - For automation-driven text generation via ai_task.generate_data All 34 tests passing. 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
Project conventions, architecture overview, testing and naming rules. 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
…0.7.0) - Added Platform.AI_TASK to __init__.py PLATFORMS - Added ai_task to manifest.json dependencies - Fixed codeowners to @dzerik, documentation URLs to dzerik/ha-smartchain - Created test_ai_task.py with 7 tests: - test_ai_task_entity_init - test_generate_data_basic - test_generate_data_structured_json - test_generate_data_structured_invalid_json - test_generate_data_llm_error - test_generate_data_with_tools - test_generate_data_empty_response - Fixed ruff lint (unused imports) and format issues - Fixed noqa directives in test files - Total: 41 tests, all passing 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
- Rewrote DOCUMENTATION.md with current architecture (v0.7.0) - Replaced all GigaChain references in COMPETITIVE_ANALYSIS.md and ROADMAP.md - Updated file paths from gigachain/ to smartchain/ - Fixed ruff format and noqa directives 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
Replace pytest.ini with pyproject.toml configuration. Update CI workflows to use astral-sh/setup-uv for dependency management. 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
- Remove ai_task from manifest.json dependencies (hangs on older HA) - Dynamically detect Platform.AI_TASK availability at import time - Pin langchain packages to compatible version ranges (core<1) - Update pyproject.toml: requires-python>=3.13, add all langchain deps - Fix ResponseError test (new gigachat API signature) 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
- Add 3 new LLM providers: Ollama (local models), DeepSeek, Anthropic (Claude) - Ollama: base_url config, ChatOllama, no API key needed - DeepSeek: uses ChatOpenAI with DeepSeek base_url - Anthropic: ChatAnthropic with claude-sonnet-4-6 default - Config flow steps for all new providers - strings.json + translations (en, ru) for new providers - 51 tests passing (10 new tests for new providers) - Ruff lint + format clean 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
- README/README-ru: add Ollama, DeepSeek, Anthropic providers, fix links - CHANGELOG: add v0.8.0 section with all new features - TODO: mark v0.8.1-v0.8.3 as completed - ROADMAP: update current version, feature matrix, metrics 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
Updated with 6 providers, dependency constraints, test counts. 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
gigachat <0.2.0 uses pydantic v1 models that break on Python 3.14. gigachat 0.2.0 migrated to pydantic v2, fixing the "unable to infer type for attribute x_headers" error. 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
- Never stop until plan is complete - Commit and push after every milestone - Act autonomously - SOLID, DRY, KISS, YAGNI design principles documented 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
- 7 new Options Flow tests: form display, model submission, model_required error, custom model_user, GigaChat-specific fields (profanity/verify_ssl), OpenAI schema exclusion, empty LLM API removal - Fix OptionsFlow: remove __init__ that set self.config_entry (read-only property in HA 2025+) - Total: 58 tests passing 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
Simulates full tool calling loop: user request → LLM returns tool_call → HA executes tool → LLM gets result → LLM returns final text. Verifies iteration count, chat_log content sequence, and bind_tools call. Total: 59 tests passing. 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
Add ConfigSubentryFlow for "conversation" subentry type. Each subentry creates its own ConversationEntity + AITaskEntity with independent model, prompt, temperature, and LLM API settings. - config_flow.py: add async_get_supported_subentry_types(), ConversationSubentryFlow with async_step_user() and async_step_reconfigure() - __init__.py: iterate entry.subentries to create per-agent clients - conversation.py: accept subentry_id + options, use _agent_options and _client properties - ai_task.py: same subentry-aware pattern - strings.json + translations: add config_subentries.conversation section (en + ru) - Backward compatible: entries without subentries use legacy options path - Version bump to 0.9.0 - 59 tests passing, lint clean 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
- Subentry flow: show form, create agent, model_required error, custom model - Setup with subentries: single agent, multiple agents, legacy fallback - Conversation entity with subentry options - Total: 67 tests passing 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
- TODO.md: mark v0.9 sub-entries, Options Flow tests, E2E test as done - CHANGELOG.md: add v0.9.0 section with sub-entries, tests, fixes - ROADMAP.md: bump to v0.9.0, update architecture diagram, feature matrix - COMPETITIVE_ANALYSIS.md: bump version to 0.9.0 - README.md + README-ru.md: add sub-entries to key features list 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
Updates the requirements on [langchain-ollama](https://github.com/langchain-ai/langchain) to permit the latest version. - [Release notes](https://github.com/langchain-ai/langchain/releases) - [Commits](langchain-ai/langchain@langchain-ollama==0.3.0...langchain-ollama==1.0.1) --- updated-dependencies: - dependency-name: langchain-ollama dependency-version: 1.0.1 dependency-type: direct:development ... Signed-off-by: dependabot[bot] <support@github.com>
dependabot
Bot
added
dependencies
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
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.
Updates the requirements on langchain-ollama to permit the latest version.
Release notes
Sourced from langchain-ollama's releases.
Commits
5842110release(ollama): 1.0.1 (#34330)62db04crevert: make integration tests output verbose (#34329)fb892eefeat(groq): Allow kwargs in with_structured_output to override tool_choice (#...8ad0e9fchore(infra,openai): make integration tests output verbose (#34327)d0b13e9release(openai): 1.1.3 (#34325)6fa4a45chore(anthropic): bump min core version (#34326)97dd5f2release(anthropic): 1.3.0 (#34324)2a82fbctest(ollama): Add unit test forChatOllamareasoning parameter (#34095)0e5e33bfix(openai): correct image resize aspect ratio caps (#34192)7829b72fix(mistralai): handle null content in tool call responses (#34268)You can trigger a rebase of this PR by commenting
@dependabot rebase.Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR:
@dependabot rebasewill rebase this PR@dependabot recreatewill recreate this PR, overwriting any edits that have been made to it@dependabot show <dependency name> ignore conditionswill show all of the ignore conditions of the specified dependency@dependabot ignore this major versionwill close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)@dependabot ignore this minor versionwill close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)@dependabot ignore this dependencywill close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)