{{ message }}
Repository navigation
Add Gemini 3.1 Pro and Inception Mercury-2 model support - #4847
Merged
Merged
Conversation
added 3 commits
February 23, 2026 02:09
Synced from cloud PR: https://github.com/Skyvern-AI/skyvern-cloud/pull/8926 Author: @suchintan ## Summary - **Gemini 3.1 Pro**: Added direct Gemini API config (`GEMINI_3.1_PRO`) and Vertex AI config (`VERTEX_GEMINI_3.1_PRO`) with `thinking_level` support, router fallback configs with GPT-5 (`GEMINI_3_1_PRO_WITH_FALLBACK`), cloud fallback overrides in `cloud/config.py`, and handler map entries for both primary and secondary handlers - **Inception Mercury-2**: Added OpenAI-compatible API integration (`INCEPTION_MERCURY_2`) at `api.inceptionlabs.ai/v1` with 128K max completion tokens. New settings: `ENABLE_INCEPTION`, `INCEPTION_API_KEY`, `INCEPTION_API_BASE` - Added model-name-to-LLM-key mappings for both models in `get_model_name_to_llm_key()` ## Test plan - [x] All modified files pass `py_compile` - [x] All pre-commit hooks pass - [x] Tested Inception Mercury-2 locally — ran a task against Hacker News with avg LLM request time of 1.72s 🤖 Generated with [Claude Code](https://claude.ai/code)
Synced from cloud PR: https://github.com/Skyvern-AI/skyvern-cloud/pull/8926 Author: @suchintan ## Summary - **Gemini 3.1 Pro**: Added direct Gemini API config (`GEMINI_3.1_PRO`) and Vertex AI config (`VERTEX_GEMINI_3.1_PRO`) with `thinking_level` support, router fallback configs with GPT-5 (`GEMINI_3_1_PRO_WITH_FALLBACK`), cloud fallback overrides in `cloud/config.py`, and handler map entries for both primary and secondary handlers - **Inception Mercury-2**: Added OpenAI-compatible API integration (`INCEPTION_MERCURY_2`) at `api.inceptionlabs.ai/v1` with 128K max completion tokens. New settings: `ENABLE_INCEPTION`, `INCEPTION_API_KEY`, `INCEPTION_API_BASE` - Added model-name-to-LLM-key mappings for both models in `get_model_name_to_llm_key()` ## Test plan - [x] All modified files pass `py_compile` - [x] All pre-commit hooks pass - [x] Tested Inception Mercury-2 locally — ran a task against Hacker News with avg LLM request time of 1.72s 🤖 Generated with [Claude Code](https://claude.ai/code)
Synced from cloud PR: https://github.com/Skyvern-AI/skyvern-cloud/pull/8926 Author: @suchintan ## Summary - **Gemini 3.1 Pro**: Added direct Gemini API config (`GEMINI_3.1_PRO`) and Vertex AI config (`VERTEX_GEMINI_3.1_PRO`) with `thinking_level` support, router fallback configs with GPT-5 (`GEMINI_3_1_PRO_WITH_FALLBACK`), cloud fallback overrides in `cloud/config.py`, and handler map entries for both primary and secondary handlers - **Inception Mercury-2**: Added OpenAI-compatible API integration (`INCEPTION_MERCURY_2`) at `api.inceptionlabs.ai/v1` with 128K max completion tokens. New settings: `ENABLE_INCEPTION`, `INCEPTION_API_KEY`, `INCEPTION_API_BASE` - Added model-name-to-LLM-key mappings for both models in `get_model_name_to_llm_key()` ## Test plan - [x] All modified files pass `py_compile` - [x] All pre-commit hooks pass - [x] Tested Inception Mercury-2 locally — ran a task against Hacker News with avg LLM request time of 1.72s 🤖 Generated with [Claude Code](https://claude.ai/code)
AronPerez
pushed a commit
to AronPerez/skyvern
that referenced
this pull request
Feb 25, 2026
…4847) Co-authored-by: Suchintan Singh <suchintan@skyvern.com>
This branch was successfully deployed
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.
Synced from cloud PR: https://github.com/Skyvern-AI/skyvern-cloud/pull/8926
Author: @suchintan
Summary
GEMINI_3.1_PRO) and Vertex AI config (VERTEX_GEMINI_3.1_PRO) withthinking_levelsupport, router fallback configs with GPT-5 (GEMINI_3_1_PRO_WITH_FALLBACK), cloud fallback overrides incloud/config.py, and handler map entries for both primary and secondary handlersINCEPTION_MERCURY_2) atapi.inceptionlabs.ai/v1with 128K max completion tokens. New settings:ENABLE_INCEPTION,INCEPTION_API_KEY,INCEPTION_API_BASEget_model_name_to_llm_key()Test plan
py_compile🤖 Generated with Claude Code