[PR #53] [MERGED] Fix Gemini 3 model names to match actual API #57

New issue

Closed

opened 2026-03-02 04:08:04 +03:00 by kerem · 0 comments

kerem commented

2026-03-02 04:08:04 +03:00

Owner

📋 Pull Request Information

Original PR: https://github.com/gadievron/raptor/pull/53
Author: @gadievron
Created: 12/25/2025
Status: ✅ Merged
Merged: 1/13/2026
Merged by: @danielcuthbert

Base: main ← Head: fix/gemini-3-correct-models

📝 Commits (10+)

c3c3320 Add auto thinking model selection and update to latest versions
d8c57eb Fix Cursor bot issues on PR #50
2b34b28 Fix inconsistent model name format in fallback
8951ffc Fix API key extraction and explicit null handling
097326f Fix non-list model_list value crashes iteration loop
925805f Fix null api_key handling and cost calculation
26a91c7 Fix invalid provider when matching by model name alias
f1a2e57 Fix null model_name and underlying_model causing TypeError
bbf4cc6 Fix empty YAML config causing AttributeError
d89bb1c Fix Gemini 3 model names to match actual API

📊 Changes

1 file changed (+1 additions, -1 deletions)

View changed files

📝 packages/llm_analysis/llm/config.py (+1 -1)

📄 Description

Summary

Fix incorrect Gemini model names that cause 404 errors
gemini-3-deep-think → gemini-3-pro-preview (no separate deep-think variant)
gemini-3-pro → gemini-3-pro-preview / gemini-3-flash-preview
Update max_tokens from 8192 to 65536

Verification

Tested via Google API - confirmed gemini-3-pro-preview and gemini-3-flash-preview are correct names. Both have thinking built-in.

🤖 Generated with Claude Code

Note

Aligns Gemini 3 model identifiers and defaults with the actual API.

Replace gemini-3-deep-think with gemini-3-pro-preview and gemini-3-pro with gemini-3-flash-preview in thinking-model selection and fallbacks

Set Gemini default primary model to gemini-3-pro-preview with max_tokens 65536; update fallbacks to use gemini-3-pro-preview and gemini-3-flash-preview

Adjust Gemini cost settings (pro-preview 0.0001, flash-preview 0.00005) and increase max_tokens from 8192 to 65536 where applicable

Update comments/docstrings to reflect new model names and reasoning support

^{Written by Cursor Bugbot for commit d89bb1cf05. This will update automatically on new commits. Configure here.}

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/gadievron/raptor/pull/53 **Author:** [@gadievron](https://github.com/gadievron) **Created:** 12/25/2025 **Status:** ✅ Merged **Merged:** 1/13/2026 **Merged by:** [@danielcuthbert](https://github.com/danielcuthbert) **Base:** `main` ← **Head:** `fix/gemini-3-correct-models` --- ### 📝 Commits (10+) - [`c3c3320`](https://github.com/gadievron/raptor/commit/c3c332082f306c7e484ff42fff86ddb01c28b51d) Add auto thinking model selection and update to latest versions - [`d8c57eb`](https://github.com/gadievron/raptor/commit/d8c57ebc53a2ead3884a6d5ca2cd108ad133de5d) Fix Cursor bot issues on PR #50 - [`2b34b28`](https://github.com/gadievron/raptor/commit/2b34b2833ea46943981bddcc1e72a4a566baf787) Fix inconsistent model name format in fallback - [`8951ffc`](https://github.com/gadievron/raptor/commit/8951ffcae8531b8db685c67fa8bef36d1b7a0c82) Fix API key extraction and explicit null handling - [`097326f`](https://github.com/gadievron/raptor/commit/097326f8cf806232ef00408847d3f954632a36c4) Fix non-list model_list value crashes iteration loop - [`925805f`](https://github.com/gadievron/raptor/commit/925805fd8a4624299657a571773394becdc75037) Fix null api_key handling and cost calculation - [`26a91c7`](https://github.com/gadievron/raptor/commit/26a91c78b1f35fd20892f409658a5a7300cd3b12) Fix invalid provider when matching by model name alias - [`f1a2e57`](https://github.com/gadievron/raptor/commit/f1a2e57daf55bf8aefa9b6fcf0a32dd8ad36c936) Fix null model_name and underlying_model causing TypeError - [`bbf4cc6`](https://github.com/gadievron/raptor/commit/bbf4cc6c1fbcb53cb1015bd94d58548912eb300e) Fix empty YAML config causing AttributeError - [`d89bb1c`](https://github.com/gadievron/raptor/commit/d89bb1cf05b7824aa32adad7b6a0c3560d672529) Fix Gemini 3 model names to match actual API ### 📊 Changes **1 file changed** (+1 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `packages/llm_analysis/llm/config.py` (+1 -1) </details> ### 📄 Description ## Summary - Fix incorrect Gemini model names that cause 404 errors - `gemini-3-deep-think` → `gemini-3-pro-preview` (no separate deep-think variant) - `gemini-3-pro` → `gemini-3-pro-preview` / `gemini-3-flash-preview` - Update max_tokens from 8192 to 65536 ## Verification Tested via Google API - confirmed `gemini-3-pro-preview` and `gemini-3-flash-preview` are correct names. Both have thinking built-in. 🤖 Generated with [Claude Code](https://claude.com/claude-code)  --- > [!NOTE] > Aligns Gemini 3 model identifiers and defaults with the actual API. > > - Replace `gemini-3-deep-think` with `gemini-3-pro-preview` and `gemini-3-pro` with `gemini-3-flash-preview` in thinking-model selection and fallbacks > - Set Gemini default primary model to `gemini-3-pro-preview` with `max_tokens` 65536; update fallbacks to use `gemini-3-pro-preview` and `gemini-3-flash-preview` > - Adjust Gemini cost settings (`pro-preview` 0.0001, `flash-preview` 0.00005) and increase `max_tokens` from 8192 to 65536 where applicable > - Update comments/docstrings to reflect new model names and reasoning support > > <sup>Written by [Cursor Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit d89bb1cf05b7824aa32adad7b6a0c3560d672529. This will update automatically on new commits. Configure [here](https://cursor.com/dashboard?tab=bugbot).</sup>  --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>