69 commits

Author	SHA1	Message	Date
tanzhenxin	89e3c2cd7a	refactor(debug): replace ConsolePatcher with debugLogger and update error reporting ... - Replace ConsolePatcher with centralized debugLogger utility - Refactor errorReporting to use debugLogger instead of file-based reporting - Remove user-facing console message components: - Delete ConsolePatcher.ts, useConsoleMessages.ts/hook - Delete ConsoleSummaryDisplay.tsx, DetailedMessagesDisplay.tsx - Update all tests in packages/core and packages/cli: - Mock debugLogger where needed - Remove assertions for console output on non-critical errors - Keep debugLogger assertions for fatal/network errors - Use HOME directory mocking for hermetic file system tests Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-02-02 17:37:54 +08:00
tanzhenxin	b804b1f48a	feat: Redesign CLI welcome screen and improve visual consistency	2026-01-16 11:48:31 +08:00
tanzhenxin	17129024f4	Add Gemini provider, remove legacy Google OAuth, and tune generation defaults	2025-12-19 16:26:54 +08:00
tanzhenxin	3e2a2255ee	DeepSeek V3.2 Thinking Mode Integration (#1134)	2025-12-05 15:08:35 +08:00
tanzhenxin	0a75d85ac9	Session-Level Conversation History Management (#1113)	2025-12-03 18:04:48 +08:00
tanzhenxin	eb95c131be	Sync upstream Gemini-CLI v0.8.2 (#838)	2025-10-23 09:27:04 +08:00
Mingholy	40810945e0	fix: add missing trace info and cancellation events (#791) ... * fix: add missing trace info and cancellation events * fix: re-organize tool/request cancellation logging	2025-10-14 15:41:30 +08:00
Mingholy	48d8587bf9	feat: add yolo mode support to auto vision model switch (#652) ... * feat: add yolo mode support to auto vision model switch * feat: add cli args & env variables for switch behavoir * fix: use dedicated model names and settings * docs: add vision model instructions * fix: failed test case * fix: setModel failure	2025-09-24 10:21:09 +08:00
Mingholy	761833c915	Vision model support for Qwen-OAuth (#525) ... * refactor: openaiContentGenerator * refactor: optimize stream handling * refactor: re-organize refactored files * fix: unit test cases * feat: `/model` command for switching to vision model * fix: lint error * feat: add image tokenizer to fit vlm context window * fix: lint and type errors * feat: add `visionModelPreview` to control default visibility of vision models * fix: remove deprecated files * fix: align supported image formats with bailian doc	2025-09-18 13:32:00 +08:00
mingholy.lmh	14ea33063f	Merge tag 'v0.3.0' into chore/sync-gemini-cli-v0.3.0	2025-09-11 16:26:56 +08:00
tanzhenxin	2572faf726	# 🚀 Sync Gemini CLI v0.2.1 - Major Feature Update (#483)	2025-09-01 14:48:55 +08:00
fuyou	45fff8f9f7	Fix(command): line/block Comments Incorrectly Parsed as Slash Commands (#6957) ... Co-authored-by: Abhi <43648792+abhipatel12@users.noreply.github.com>	2025-08-26 03:51:27 +00:00
Pascal Birchler	0f031a7f89	Explict imports & exports with type modifier (#3774)	2025-08-25 22:04:53 +00:00
shishu314	cd75d94262	Log yolo mode + number of turns (#6055) ... Co-authored-by: Shi Shu <shii@google.com>	2025-08-25 20:06:47 +00:00
Pascal Birchler	49cce8a15d	chore(test): install and configure vitest eslint plugin (#3228) ... Co-authored-by: N. Taylor Mullen <ntaylormullen@google.com>	2025-08-25 14:21:47 +00:00
Tommaso Sciortino	75822d3506	Change the type of ToolResult.responseParts (#6875)	2025-08-22 21:12:05 +00:00
Victor May	bb8a23ae80	Retry Message Stream on Empty Chunks (#6777)	2025-08-22 19:43:53 +00:00
Victor May	4642de2a5c	Fixing at command race condition (#6663)	2025-08-20 19:51:31 +00:00
mingholy.lmh	c546d86d44	Merge tag 'v0.1.21' of github.com:google-gemini/gemini-cli into chore/sync-gemini-cli-v0.1.21	2025-08-20 22:24:50 +08:00
tanzhenxin	7dbc240847	chore: sync gemini-cli v0.1.19	2025-08-18 19:55:46 +08:00
tanzhenxin	0265b67b90	chore: npm run format & lint	2025-08-14 16:48:51 +08:00
tanzhenxin	c58106079e	feat: prevent concurrent query submissions in useGeminiStream hook	2025-08-14 16:39:26 +08:00
Adam Weidman	b61a63aef4	move errorParsing.ts to core (#6159)	2025-08-13 17:57:11 +00:00
Jacob Richman	d219f90132	Switch from useInput to useKeypress. (#6056)	2025-08-12 21:05:49 +00:00
shishu314	1f0ad86544	fix: Restore user input when the user cancels response (#5601) ... Co-authored-by: Shi Shu <shii@google.com> Co-authored-by: Jacob Richman <jacob314@gmail.com>	2025-08-06 19:19:10 +00:00
joshualitt	6133bea388	feat(core): Introduce DeclarativeTool and ToolInvocation. (#5613)	2025-08-06 17:50:02 +00:00
Yiheng Xu	cd375fefe5	sync gemini-cli 0.1.17 ... Co-Authored-By: Qwen-Coder <qwen-coder@alibabacloud.com>	2025-08-05 17:09:19 +08:00
Pyush Sinha	e506b40c27	fix: /help remove flickering and respect clear shortcut (ctr+l) (#3611) ... Co-authored-by: Jacob Richman <jacob314@gmail.com> Co-authored-by: Allen Hutchison <adh@google.com>	2025-08-04 16:53:50 +00:00
Pyush Sinha	ca19aa9125	fix: /help remove flickering and respect clear shortcut (ctr+l) (#3611) ... Co-authored-by: Jacob Richman <jacob314@gmail.com> Co-authored-by: Allen Hutchison <adh@google.com>	2025-08-04 16:53:50 +00:00
奕桁	b69b2ce376	Merge tag 'v0.1.15' into feature/yiheng/sync-gemini-cli-0.1.15	2025-08-01 23:06:11 +08:00
Neha Prasad	a5ea113a8e	fix: Clear previous thoughts when starting new prompts (#4966)	2025-07-28 17:57:33 +00:00
Neha Prasad	4b3e407d49	fix: Clear previous thoughts when starting new prompts (#4966)	2025-07-28 17:57:33 +00:00
Fan	daad04613e	pre-release: fix ci (#1) ... * fix aoneci * remove codeql * sync version to 0.0.1-alpha.7 * renaming org to qwen-code	2025-07-22 09:27:14 -07:00
koalazf.99	a9d6965bef	pre-release commit	2025-07-22 23:26:01 +08:00
Abhi	9daead63dd	(feat): Initial Version of Custom Commands (#4572)	2025-07-22 04:34:55 +00:00
darkcocoa	4c3532d2b3	fix: Add warning message for token limit truncation (#2260) ... Co-authored-by: Sandy Tao <sandytao520@icloud.com>	2025-07-21 21:57:11 +00:00
uttamkanodia14	93284281de	Logs the auth type in the user prompts, api responses and errors (#3795)	2025-07-11 16:47:46 +00:00
uttamkanodia14	063481faa4	Adding TurnId to Tool call and API responses and error logs. (#3039) ... Co-authored-by: Scott Densmore <scottdensmore@mac.com>	2025-07-09 18:49:30 +00:00
Bryan Morgan	8a6509ffeb	Remove auto-execution on Flash in the event of a 429/Quota failover (#3662) ... Co-authored-by: Jenna Inouye <jinouye@google.com>	2025-07-09 17:55:56 +00:00
Bryan Morgan	b0cce95286	Improve quota- and resource-related 429 error handling, also taking Code Assist customer tiers into consideration (#3609)	2025-07-09 14:18:15 +00:00
Abhi	aa10ccba71	feature(commands) - Refactor Slash Command + Vision For the Future (#3175)	2025-07-07 20:45:44 +00:00
N. Taylor Mullen	4be32d1f73	fix(cli): Group cancelled tool call responses to prevent API errors (#3333)	2025-07-05 20:56:39 +00:00
Tommaso Sciortino	3587054d32	Rename AuthType LOGIN_WITH_GOOGLE_PERSONAL -> LOGIN_WITH_GOOGLE (#2769)	2025-07-01 00:11:54 +00:00
Abhi	770f862832	feat: Change /stats to include more detailed breakdowns (#2615)	2025-06-30 00:44:33 +00:00
Sandy Tao	150df382f8	Upgrade to Ink 6 and React 19 (#2096) ... Co-authored-by: jacob314 <jacob314@gmail.com>	2025-06-27 23:39:54 +00:00
Tommaso Sciortino	79c647d486	Merge "Login with Google Workspace" auth option into "Login with Google" (#1574) ... Co-authored-by: Scott Densmore <scottdensmore@mac.com>	2025-06-25 22:38:18 +00:00
Brandon Keiji	f6c36f75e3	fix: prepublish changes to package names (#1420)	2025-06-25 12:41:11 +00:00
Abhi	d3f13c71ae	feat: add custom message for 429 errors (#1366)	2025-06-24 03:43:00 +00:00
Jerop Kipruto	b443b5e800	Ensure telemetry events are flushed immediately (#1344) ... The previous implementation used `flushIfNeeded` to batch most telemetry events, but it was not reliably sending them, leading to data loss. Notably, the `startSession` event, which already used `flushToClearcut`, was working correctly, indicating an issue with the batching logic itself. This change replaces all calls to `flushIfNeeded` with `flushToClearcut` to align all event logging with the working `startSession` implementation and ensure that events are sent immediately. This prioritizes the reliability of data collection over network efficiency. This is a temporary solution to prevent further data loss. The underlying issue with the batching mechanism in `flushIfNeeded` should be investigated and fixed in the future, at which point this change can be reverted.	2025-06-23 22:05:02 +00:00
Jerop Kipruto	98f3a7066e	refactor: rename disableDataCollection to dataCollectionEnabled (#1319) ... Renames the `disableDataCollection` flag to the more intuitive and positive `dataCollectionEnabled`. This change improves code clarity by avoiding double negatives and making the purpose of the flag more direct. The logic has been inverted wherever the flag is used to accommodate the new naming convention. Using a suffix like `"Enabled"` follows a common convention that improves readability. - A condition like `if (dataCollectionEnabled)` reads like a natural language sentence ("if data collection is enabled"), which reduces cognitive load. - Distinguishes the boolean flag (representing a state) from potential functions that would perform an action (e.g., `enableDataCollection()` or `disableDataCollection()`), avoiding ambiguity between checking a value and calling a function. #750	2025-06-23 21:19:40 +00:00