a24009f9c0
fix(patch): cherry-pick d96bd05 to release/v0.30.0-preview.5-pr-19867 to patch version v0.30.0-preview.5 and create version 0.30.0-preview.6 ( #20112 )
...
Co-authored-by: Bryan Morgan <bryanmorgan@google.com >
2026-02-24 01:57:13 +00:00
9ddc46c59a
update isActiveModel to return false for unknown models
2026-02-19 17:40:51 -05:00
ed8f7f6766
feat(models): support Gemini 3.1 custom tool model ( #131 )
...
* feat(models): add support for Gemini 3.1 and custom tool models
* test(routing): fix classifier and numerical classifier strategy tests
* test(routing): add Gemini 3.1 tests for classifier strategy
* fix(models): correctly filter active Gemini 3.1 models
* fix(routing): ensure useCustomToolModel is only true when Gemini 3.1 is enabled
* fix(test-utils): prevent double newline in lastFrame() on Windows
* fix(test-utils): surgically fix double newline in lastFrame() on Windows
* use custom_tools_model string for api key only
* fix(ui): correct useCustomToolModel logic and update tests
* fix(ui): correct useCustomToolModel logic in StatsDisplay
* fix(routing): ensure test models are active and sync useCustomToolModel logic
2026-02-19 14:13:33 -05:00
f669adbffd
feat(core,ui): support Gemini 3.1 Pro Preview and active model filtering ( #125 )
...
* feat(core,ui): support Gemini 3.1 Pro Preview and active model filtering
* fix(core,ui): use optional chaining for config methods to support mocks
* fix(core): clear stale authType in refreshAuth to avoid incorrect model resolution
* do not show gemini 3.1 model when users do not have access to gemini 3.1 in stats
2026-02-19 11:47:20 -05:00
39d36108d7
feat(core): support custom reasoning models by default ( #19227 )
2026-02-16 20:47:58 +00:00
37f128a109
feat(routing): restrict numerical routing to Gemini 3 family ( #18478 )
2026-02-10 14:25:21 +00:00
61d92c4a21
Remove previewFeatures and default to Gemini 3 ( #18414 )
2026-02-06 18:02:57 +00:00
ed0b0fae49
fix(core): resolve auto model in default strategy ( #17116 )
2026-01-20 21:03:34 +00:00
a1dd19738e
feat(core): Preliminary changes for subagent model routing. ( #16035 )
2026-01-07 21:21:10 +00:00
cbd2eee9c4
remove manual string when displaying manual model in the footer ( #15967 )
2026-01-06 04:07:44 +00:00
d6a2f1d670
chore(core): refactor model resolution and cleanup fallback logic ( #15228 )
2025-12-22 15:18:51 +00:00
bf90b59935
feat: launch Gemini 3 Flash in Gemini CLI ⚡ ️ ⚡ ️ ⚡ ️ ( #15196 )
...
Co-authored-by: gemini-cli-robot <gemini-cli-robot@google.com >
Co-authored-by: joshualitt <joshualitt@google.com >
Co-authored-by: Sehoon Shon <sshon@google.com >
Co-authored-by: Adam Weidman <65992621+adamfweidman@users.noreply.github.com >
Co-authored-by: Adib234 <30782825+Adib234@users.noreply.github.com >
Co-authored-by: Jenna Inouye <jinouye@google.com >
2025-12-17 09:43:21 -08:00
d236df5b21
Fix tool output fragmentation by encapsulating content in functionResponse ( #13082 )
2025-12-15 20:36:34 +00:00
2800187355
feat: display quota stats for unused models in /stats ( #14764 )
2025-12-09 20:09:46 +00:00
86828bb561
feat: launch Gemini 3 in Gemini CLI 🚀 🚀 🚀 (in main) ( #13287 )
...
Co-authored-by: Adam Weidman <65992621+adamfweidman@users.noreply.github.com >
Co-authored-by: Sehoon Shon <sshon@google.com >
Co-authored-by: Adib234 <30782825+Adib234@users.noreply.github.com >
Co-authored-by: Sandy Tao <sandytao520@icloud.com >
Co-authored-by: Abhi <43648792+abhipatel12@users.noreply.github.com >
Co-authored-by: Aishanee Shah <aishaneeshah@gmail.com >
Co-authored-by: gemini-cli-robot <gemini-cli-robot@google.com >
Co-authored-by: Gal Zahavi <38544478+galz10@users.noreply.github.com >
Co-authored-by: Jacob Richman <jacob314@gmail.com >
Co-authored-by: joshualitt <joshualitt@google.com >
Co-authored-by: Jenna Inouye <jinouye@google.com >
2025-11-18 09:01:16 -08:00
59e0b10e6c
Cap Thinking Budget to prevent runaway thought loops ( #12416 )
2025-11-03 18:39:06 +00:00
c15774ce68
# feat(routing): Introduce useModelRouter feature flag ( #8366 )
2025-09-12 19:57:07 +00:00
538e6cd19a
feat(routing): Initialize model routing architecture ( #8153 )
2025-09-11 17:38:50 +00:00
f2bddfe054
fix: add flash lite with respect to api defaults ( #4652 )
...
Co-authored-by: Gal Zahavi <38544478+galz10@users.noreply.github.com >
2025-08-29 16:20:50 +00:00
dccca91fc9
Switch utility calls to use the gemini-2.5-flash-lite model ( #5193 )
...
Co-authored-by: Anjali Sridhar <anjsridhar@gmail.com >
2025-08-01 21:11:51 +00:00
0b5cc96362
(model) - Use Flash Lite For Next Speaker Checks ( #4991 )
2025-07-27 21:40:55 +00:00
787c319e87
feat: Update default Gemini Flash model to 2.5 ( #1241 )
2025-06-20 05:54:00 +00:00
0da4fd9d11
feat: update default gemini model to GA 2.5 pro ( #1173 )
2025-06-17 23:08:04 -07:00
7bcc60e996
refactor: Use default centralized Flash & Pro models everywhere ( #994 )
2025-06-13 08:25:42 +00:00
gemini-cli-robot