Update to llm 0.33; various test and development changes - #66
Merged
Merged
Conversation
Decouple tests from live model catalog IDs which can get stale.
==== kimi-k3: Thread the capability through VeniceChat/AsyncVeniceChat/VeniceImage/ AsyncVeniceImage constructors and registration instead of post-hoc attribute assignment. Migrate tests to declare capability at construction or via the hermetic model catalog, and add a CLI regression test that exercises the real model-resolution path. Fixes the dead-code pattern where tests mutated a throwaway llm.get_model() instance the CLI never used.
Change test_chat.py to mock VeniceChat.execute to match LLM 0.33 conversation routing
There was a problem hiding this comment.
🟢 Approval recommended
The dependency migration and capability changes are consistent and covered by focused tests.
Pull request overview
Updates the plugin for LLM 0.33 and its HTTPX2 stack while improving model capability handling and test stability.
Changes:
- Migrates HTTP calls and tests from HTTPX to HTTPX2.
- Passes web-search capability through model constructors.
- Modernizes test fixtures, JSON log assertions, and development tooling.
File summaries
| File | Description |
|---|---|
AGENTS.md |
Simplifies contributor validation instructions. |
pyproject.toml |
Updates dependencies and tool configuration. |
llm_venice/api/characters.py |
Migrates character requests to HTTPX2. |
llm_venice/api/errors.py |
Updates HTTP error types. |
llm_venice/api/keys.py |
Migrates API-key requests to HTTPX2. |
llm_venice/api/refresh.py |
Migrates model refresh requests. |
llm_venice/api/upscale.py |
Migrates image upscale requests. |
llm_venice/cli/api_keys.py |
Handles HTTPX2 request errors. |
llm_venice/cli/characters.py |
Handles HTTPX2 request errors. |
llm_venice/cli/upscale.py |
Handles HTTPX2 request errors. |
llm_venice/cli/venice_group.py |
Updates refresh error handling. |
llm_venice/models/__init__.py |
Propagates web-search capabilities. |
llm_venice/models/audio.py |
Migrates speech requests to HTTPX2. |
llm_venice/models/chat.py |
Adds capability constructors and typed options. |
llm_venice/models/image.py |
Adds capability constructors and HTTPX2 support. |
tests/conftest.py |
Adds a hermetic model-catalog fixture. |
tests/test_api_keys.py |
Updates HTTPX2 error tests. |
tests/test_audio.py |
Updates speech request mocks. |
tests/test_characters.py |
Updates HTTPX2 error tests. |
tests/test_chat.py |
Uses hermetic models and tests capability propagation. |
tests/test_image.py |
Updates mocks and constructor usage. |
tests/test_image_upscale.py |
Updates timeout tests for HTTPX2. |
tests/test_integration.py |
Reads structured prompt JSON output. |
tests/test_integration_comprehensive.py |
Updates citation integration assertions. |
tests/test_model_registration.py |
Tests catalog capability propagation. |
tests/test_refresh.py |
Updates HTTPX2 timeout tests. |
Review details
- Files reviewed: 26/26 changed files
- Comments generated: 0
- Review effort level: Balanced
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
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
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.
missingDefaultExcludeswarning.supports_web_searcha constructor parameter.VeniceChatOptionsinherited fields for pyright compatibility.prompt --json.