feat: Add support for custom Gemini models and model loading strategies #86
+601
−312
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
Collaborator
luuquangvu
commented
Jan 13, 2026
luuquangvu
commented
- Add support for custom Gemini models and model loading strategies.
- Move all helper functions to utils/helper.
- Update documentation to reflect changes in model configuration.
They are no longer needed since the underlying library issue has been resolved.
…to better handle heavy tasks
… client status checks
…probabilities, and token details; adjust response handling accordingly.
…tput_text` validator, rename `created` to `created_at`, and update response handling accordingly.
…roved streaming of response items. Refactor image generation handling for consistency and add compatibility with output content.
…t` and ensure consistent initialization in image output handling.
…anagement Add dedicated router for /images endpoint and refactor image handling logic for better modularity. Enhance temporary image management with secure naming, token verification, and cleanup functionality.
…l and refactor variable handling
…y` for tools, tool_choice, and streaming settings
…nd update response handling for consistency
…mat for compatibility
…ck to default size
…andling, and improved extension determination
- Introduced `model_strategy` configuration for "append" (default + custom models) or "overwrite" (custom models only). - Enhanced `/v1/models` endpoint to return models based on the configured strategy. - Improved model loading with environment variable overrides and validation. - Refactored model handling logic for improved modularity and error handling.
…eld support - Enhanced `extract_gemini_models_env` to handle nested fields within environment variables. - Updated type hints for more flexibility in model overrides. - Improved `_merge_models_with_env` to better support field-level updates and appending new models.
- Moved utility functions like `strip_code_fence`, `extract_tool_calls`, and `iter_stream_segments` to a centralized helper module. - Removed unused and redundant private methods from `chat.py`, including `_strip_code_fence`, `_strip_tagged_blocks`, and `_strip_system_hints`. - Updated imports and references across modules for consistency. - Simplified tool call and streaming logic by replacing inline implementations with shared helper functions.
- Replaced unused model placeholder in `config.yaml` with an empty list. - Added JSON parsing validators for `model_header` and `models` to enhance flexibility and error handling. - Improved validation to filter out incomplete model configurations.
…N support - Replaced prefix-based parsing with a root key approach. - Added JSON parsing to handle list-based model configurations. - Improved handling of errors and cleanup of environment variables.
…to Python literals - Added `ast.literal_eval` as a fallback for parsing environment variables when JSON decoding fails. - Improved error handling and logging for invalid configurations. - Ensured proper cleanup of environment variables post-parsing.
- Adjusted `TOOL_CALL_RE` regex pattern for better accuracy.
…nvironment variable setup
Nativu5
requested changes
Jan 14, 2026
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adds support for custom Gemini models with configurable loading strategies. It refactors helper functions into a dedicated utils module and updates documentation to reflect the new model configuration options.
Changes:
- Added custom Gemini model configuration with "append" and "overwrite" strategies
- Consolidated helper functions from app/server/chat.py into app/utils/helper.py
- Added environment variable support for custom model configuration
Reviewed changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 4 comments.
Show a summary per file
| File | Description |
|---|---|
| config/config.yaml | Added model_strategy and models fields for custom model configuration |
| app/utils/helper.py | Moved and added helper functions including tool call extraction, streaming, and image processing utilities |
| app/utils/config.py | Added GeminiModelConfig class and model configuration parsing with environment variable support |
| app/services/client.py | Removed XML_WRAP_HINT and CODE_BLOCK_HINT constants now imported from helper.py |
| app/server/chat.py | Refactored to use helper functions, added _get_model_by_name and _get_available_models for custom model support, improved image generation error handling |
| README.md | Added documentation for custom model configuration |
| README.zh.md | Added Chinese documentation for custom model configuration and minor formatting fix |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
…nvironment variables; enhance error logging in config validation
…tring or list structure for enhanced flexibility in automated environments
Nativu5
approved these changes
Jan 15, 2026
Collaborator
Author
|
@Nativu5 Thank you! |
Collaborator
Author
|
I would like to request permission to merge this PR. Thank you again @Nativu5 ! |
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.