Commit Graph

72 Commits

Author SHA1 Message Date
jacob314 2717cacb8c test(cli): fix flaky QuotaDisplay snapshot and env leakage in StatusDisplay 2026-03-02 12:22:11 -08:00
Yuna Seol 8aca3068cf feat: add role-specific statistics to telemetry and UI (cont. #15234) (#18824)
Co-authored-by: Yuna Seol <yunaseol@google.com>
2026-02-17 17:32:30 +00:00
Sehoon Shon 61d92c4a21 Remove previewFeatures and default to Gemini 3 (#18414) 2026-02-06 18:02:57 +00:00
Pyush Sinha addecf2c74 fix(core): update token count and telemetry on /chat resume history load (#16279)
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>
2026-01-21 21:24:33 +00:00
Vedant Mahajan e92f60b4fc fix: migrate BeforeModel and AfterModel hooks to HookSystem (#16599)
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>
2026-01-20 17:46:54 +00:00
Sandy Tao e1e3efc9d0 feat(hooks): Support explicit stop and block execution control in model hooks (#15947)
Co-authored-by: matt korwel <matt.korwel@gmail.com>
2026-01-09 05:36:27 +00:00
Adam Weidman bf6d0485ce chore(core): remove legacy fallback flags and migrate loop detection (#15213) 2025-12-17 22:14:33 +00:00
joshualitt de7e1937f6 feat(core): Late resolve GenerateContentConfigs and reduce mutation. (#14920) 2025-12-17 20:29:26 +00:00
Adam Weidman b465e12747 chore(core): remove redundant isModelAvailabilityServiceEnabled toggle and clean up dead code (#15207) 2025-12-17 19:23:56 +00:00
Tommaso Sciortino 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
Christian Gunderman 942bcfc61e Disallow redundant typecasts. (#15030) 2025-12-13 01:43:43 +00:00
Adam Weidman 8f4f8baa81 feat(modelAvailabilityService): integrate model availability service into backend logic (#14470) 2025-12-08 14:44:34 +00:00
matt korwel dd3fd73ffe fix(core): improve API response error handling and retry logic (#14563) 2025-12-05 17:49:08 +00:00
Marat Boshernitsan b9b3b8050d Allow telemetry exporters to GCP to utilize user's login credentials, if requested (#13778) 2025-12-03 05:27:37 +00:00
CHAEWAN KIM f4babf172b fix(async): prevent missed async errors from bypassing catch handlers (#13714)
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com>
2025-12-01 22:11:40 +00:00
Edilmo Palencia 5bed97064a feat(hooks): Hook LLM Request/Response Integration (#9110) 2025-11-26 23:51:28 +00:00
Sandy Tao e1d2653a7a feat(core): Improve request token calculation accuracy (#13824) 2025-11-26 04:20:46 +00:00
joshualitt fe67ef63c1 bug(core): Ensure we use thinking budget on fallback to 2.5 (#13596) 2025-11-21 17:43:20 +00:00
joshualitt 8c07ad2ab9 feat(core): Use thinking level for Gemini 3 (#13445) 2025-11-20 19:19:52 +00:00
joshualitt 257cd07a3a feat(core): Wire up chat code path for model configs. (#12850) 2025-11-20 04:41:16 +00:00
Shreya Keshive 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
Tommaso Sciortino fb03242950 Improve MALFORMED_FUNCTION_CALL handling (#12965) 2025-11-13 16:07:49 +00:00
N. Taylor Mullen 7bb13d1c41 telemetry: track interactive session state (#12856)
Co-authored-by: owenofbrien <86964623+owenofbrien@users.noreply.github.com>
2025-11-11 10:03:32 +00:00
Sandy Tao 322feaafa6 refactor(core): decouple GeminiChat from uiTelemetryService via Usage events (#12196) 2025-10-30 21:05:38 +00:00
Sandy Tao 7c1a90244a fix(core): add retry logic for specific fetch errors (#11066) 2025-10-14 16:17:31 +00:00
joshualitt ada179f572 bug(core): Process returned function calls sequentially. (#10659) 2025-10-13 22:52:16 +00:00
Sandy Tao 8dc397c0a5 fix(core): set temperature to 1 on retry in sendMessageStream (#10866) 2025-10-10 16:14:12 +00:00
Sandy Tao e705f45c5f fix(core): retain user message in history on stream failure (#10608) 2025-10-06 23:32:35 +00:00
Sandy Tao 3b92f127a9 refactor(core): Unify retry logic and remove schema depth check (#10453) 2025-10-03 16:08:27 +00:00
Sandy Tao ac4a79223a feat(core): Add content-based retries for JSON generation (#9264) 2025-09-29 19:27:15 +00:00
Sandy Tao e209724789 fix(core): Improve API error retry logic (#9763) 2025-09-25 17:57:00 +00:00
Sandy Tao 712dc245ac fix(quality): Retry invalid stream only 1 time (#9169) 2025-09-23 00:15:55 +00:00
Sandy Tao 4cdf9207f3 feat(core): Log invalid stream type (#9168) 2025-09-22 23:39:44 +00:00
Sandy Tao 9c4d1594ac Fix(quality): Refine Stream Validation Logic (#9150) 2025-09-22 21:40:09 +00:00
Sandy Tao 2c754d71e3 fix(ui): Track last prompt token count in processStream (#8650) 2025-09-18 18:46:56 +00:00
Tommaso Sciortino e76dda37ad Serialize function calls that mutate state (#8513) 2025-09-17 18:45:04 +00:00
Tommaso Sciortino 4e5c1fce8d Remove unused code. (#8497) 2025-09-16 19:12:45 +00:00
Abhi 538e6cd19a feat(routing): Initialize model routing architecture (#8153) 2025-09-11 17:38:50 +00:00
Tommaso Sciortino 03e3c59bf0 Fix compression issues (#8225) 2025-09-10 23:04:20 +00:00
Abhi f6f2fff724 refactor: Centralize and improve model fallback handling (#7634) 2025-09-08 20:19:52 +00:00
Tommaso Sciortino 6e26c88c2c Pull contentGenerator out of GeminiClient and into Config. (#7825) 2025-09-07 20:00:03 +00:00
Sandy Tao 13d39ef746 Fix(core): Do not retry if last chunk is empty with finishReason previous chunks are good (#7859) 2025-09-06 07:01:21 +00:00
Sandy Tao 968e938949 Fix(core): Fix stream validation logic (#7832) 2025-09-05 23:22:54 +00:00
Victor May e7a4142b2a Handle cleaning up the response text in the UI when a response stream retry occurs (#7416) 2025-09-04 02:00:16 +00:00
bl-ue b5dd6f9ea6 feat(sessions): Integrate chat recording into GeminiChat (#6721) 2025-09-03 05:29:07 +00:00
Victor May c35aebe109 Refine stream validation to prevent unnecessary retries (#7278) 2025-08-28 17:21:27 +00:00
Victor May 08bdd08412 Clearcut Logging of Content Error Metrics (#7099)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-08-26 19:37:18 +00:00
Victor May d340ddae62 Ensure a Strictly Alternating Message History (#6995)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-08-26 18:00:20 +00:00
Pascal Birchler 0f031a7f89 Explict imports & exports with type modifier (#3774) 2025-08-25 22:04:53 +00:00
Victor May 5b5290146a Metrics for Retries on Content Errors (#6870)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-08-22 23:06:29 +00:00