13603a30b7
fix(build): resolve TS4111 and TS2339 errors in config and tests
2026-05-04 16:48:18 -04:00
a976c227c2
fix(config): ensure configuration persistence and fix in-memory regressions
...
This commit addresses issue #25428 by:
1. Aligning the settings loader to use the same lenient parser (comment-json) as the saver, preventing data loss on minor JSON syntax errors.
2. Refactoring migrations to be granular instead of category-wide, protecting sibling keys from accidental deletion.
3. Expanding the hot-reload payload to ensure all configuration changes are immediately propagated to the core engine without a restart.
4. Fixing UI search result collisions for settings with duplicate labels.
2026-05-04 16:34:47 -04:00
75a8de83fc
test(cleanup): fix temporary directory leaks in test suites ( #26217 )
2026-05-04 19:08:02 +00:00
a7beb890d0
feat(memory): add Auto Memory inbox flow with canonical-patch contract ( #26338 )
2026-05-04 19:07:13 +00:00
60a6a47d56
feat(voice): add privacy and compliance UX warning for Gemini Live backend ( #26454 )
2026-05-04 18:32:15 +00:00
0da1a2026a
fix(cli)#21297: clear skills consent dialog before reload ( #26431 )
...
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com >
2026-05-04 17:53:03 +00:00
ab48aad213
perf: skip redundant GEMINI.md loading in partialConfig ( #26443 )
2026-05-04 16:05:24 +00:00
9cb48020e1
fix(cli): respect .env override for GOOGLE_CLOUD_PROJECT ( #26288 )
2026-05-01 16:49:45 +00:00
d9f273e440
feat(config): enable Gemma 4 models by default via Gemini API ( #26307 )
2026-05-01 04:14:57 +00:00
c94edcd862
fix(cli): do not override GOOGLE_CLOUD_PROJECT in Cloud Shell when using Vertex AI ( #24455 )
...
Co-authored-by: David Pierce <davidapierce@google.com >
2026-04-30 17:52:18 +00:00
d743c6fae6
fix: suppress duplicate extension warnings during startup ( #26208 )
2026-04-30 14:11:06 +00:00
0ccc5ce58f
refactor(acp): delegate prompt turn processing logic to GeminiClient ( #26222 )
2026-04-29 23:58:16 +00:00
7ab932c8bf
test: fix failures due to antigravity environment leakage ( #26162 )
2026-04-29 14:51:43 +00:00
c841070582
feat(cli): support boolean and number casting for env vars in settings.json ( #26118 )
2026-04-28 17:32:51 +00:00
b0ffa3b51e
fix(core): handle non-string model flags in resolution ( #26069 )
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-04-28 17:11:15 +00:00
6cc0b1b136
feat(cli): provide manual session UUID via command line arg ( #26060 )
2026-04-27 21:05:27 +00:00
71f313b51a
feat(core): wire up the new ContextManager and AgentChatHistory ( #25409 )
2026-04-27 18:50:00 +00:00
743518e1b8
fix(cli): add missing response key to custom theme text schema ( #25822 )
...
Co-authored-by: Adib234 <30782825+Adib234@users.noreply.github.com >
2026-04-27 15:01:30 +00:00
2e0641c83b
feat(voice): implement real-time voice mode with cloud and local backends ( #24174 )
2026-04-24 21:29:38 +00:00
d4c5333dcf
feat(core,cli): add support for Gemma 4 models (experimental) ( #25604 )
2026-04-23 23:02:17 +00:00
27927c55e5
feat(core): enhance shell command validation and add core tools allowlist ( #25720 )
...
Co-authored-by: David Pierce <davidapierce@google.com >
Co-authored-by: Keith Schaab <keithsc@google.com >
Co-authored-by: Keith Schaab <keith.schaab@gmail.com >
Co-authored-by: Emily Hedlund <ehedlund@google.com >
2026-04-23 20:26:01 +00:00
dba9b9a0ff
feat(cli): secure .env loading and enforce workspace trust in headless mode ( #25814 )
...
Co-authored-by: galz10 <galzahavi@google.com >
Co-authored-by: davidapierce <davidapierce@google.com >
2026-04-23 16:09:14 +00:00
5318610c1d
fix(core): support jsonl session logs in memory and summary services ( #25816 )
2026-04-22 23:07:39 +00:00
6edfba481f
refactor(memory): replace MemoryManagerAgent with prompt-driven memory editing across four tiers ( #25716 )
2026-04-22 01:21:55 +00:00
cdc5cccc13
feat: detect new files in @ recommendations with watcher based updates ( #25256 )
2026-04-21 18:35:14 +00:00
c260550146
feat(telemetry): add flag for enabling traces specifically ( #25343 )
2026-04-21 18:07:32 +00:00
27344833cb
feat(vertex): add settings for Vertex AI request routing ( #25513 )
2026-04-21 17:48:30 +00:00
2c14954010
Fix: Disallow overriding IDE stdio via workspace .env (RCE) ( #25022 )
...
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com >
2026-04-21 10:31:10 -07:00
1d383a4a8e
feat(cli): add streamlined gemini gemma local model setup ( #25498 )
...
Co-authored-by: Abhijit Balaji <abhijitbalaji@google.com >
Co-authored-by: Samee Zahid <sameez@google.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-04-20 23:57:56 +00:00
8573650253
feat(config): split memoryManager flag into autoMemory ( #25601 )
2026-04-18 00:08:02 +00:00
b2f775921d
feat(core): enable topic update narration by default and promote to general ( #25586 )
...
Co-authored-by: JAYADITYA <96861162+JayadityaGit@users.noreply.github.com >
Co-authored-by: Jack Wotherspoon <jackwoth@google.com >
2026-04-17 17:49:32 +00:00
ac9025e9fc
Use OSC 777 for terminal notifications ( #25300 )
2026-04-16 18:45:54 +00:00
24f9ec51d2
fix: correct redirect count increment in fetchJson ( #24896 )
...
Co-authored-by: Tommaso Sciortino <sciortino@gmail.com >
2026-04-13 20:45:52 +00:00
6b6ea56437
fix(core): fix quota footer for non-auto models and improve display ( #25121 )
2026-04-13 17:03:41 +00:00
43b93e9e1b
debugging(ui): add optional debugRainbow setting ( #25088 )
2026-04-10 02:42:21 +00:00
0690192d45
fix: respect hideContextPercentage when FooterConfigDialog is closed without changes ( #24773 )
...
Co-authored-by: Coco Sheng <cocosheng@google.com >
2026-04-09 18:17:00 +00:00
b238a453e3
feat(core): refactor subagent tool to unified invoke_subagent tool ( #24489 )
2026-04-09 16:48:24 +00:00
464bac270c
fix(cli): optimize startup with lightweight parent process ( #24667 )
2026-04-09 00:17:32 +00:00
34b4f1c6e4
refactor(plan): simplify policy priorities and consolidate read-only rules ( #24849 )
2026-04-08 15:58:29 +00:00
e7f8d9cf1a
Revert "feat: Introduce an AI-driven interactive shell mode with new"
...
This reverts commit 651ad63ed6
2026-04-08 07:31:17 -07:00
651ad63ed6
feat: Introduce an AI-driven interactive shell mode with new
...
`read-shell` and `write-to-shell` tools and a configurable mode setting.
2026-04-08 07:27:28 -07:00
7e1938c1bc
fix(cli): switch default back to terminalBuffer=false and fix regressions introduced for that mode ( #24873 )
2026-04-08 05:47:54 +00:00
986293bd38
feat(core): add agent protocol UI types and experimental flag ( #24275 )
...
Co-authored-by: Adam Weidman <adamfweidman@gmail.com >
Co-authored-by: Adam Weidman <adamfweidman@google.com >
2026-04-07 21:45:18 +00:00
df67f973ed
fix(cli): respect global environment variable allowlist ( #24767 )
2026-04-06 22:17:55 +00:00
21a3925f99
docs: update sandboxing documentation and toolSandboxing settings ( #24655 )
2026-04-04 01:26:41 +00:00
3f12c1d7c7
feat(cli): enable compact tool output by default ( #24509 ) ( #24510 )
2026-04-03 17:59:12 +00:00
61719a3926
show color ( #24613 )
2026-04-03 16:53:34 +00:00
1f5d7014c6
feat(ui): enable "TerminalBuffer" mode to solve flicker ( #24512 )
2026-04-03 00:39:49 +00:00
e0044f2868
feat(core): Land ContextCompressionService ( #24483 )
2026-04-02 16:22:04 +00:00
beff8c91aa
fix(browser): handle computer-use model detection for analyze_screenshot ( #24502 )
2026-04-02 15:05:21 +00:00
Coco Sheng