79ea865790
feat: introduce Forever Mode with A2A listener
...
- Sisyphus: auto-resume timer with schedule_work tool
- Confucius: built-in sub-agent for knowledge consolidation before compression
- Hippocampus: in-memory short-term memory via background micro-consolidation
- Bicameral Voice: proactive knowledge alignment on user input
- Archive compression mode for long-running sessions
- Onboarding dialog for first-time Forever Mode setup
- Refresh system instruction per turn so hippocampus reaches the model
- Auto-start A2A HTTP server when Forever Mode + Sisyphus enabled
- Bridge external messages into session and capture responses
- Display A2A port in status bar alongside Sisyphus timer
2026-03-06 22:03:20 -08:00
9a7427197b
fix(billing): fix overage strategy lifecycle and settings integration ( #21236 )
2026-03-07 03:14:44 +00:00
7ec477d40d
feat(acp): Add support for AI Gateway auth ( #21305 )
2026-03-05 22:15:23 +00:00
5bd21a240d
fix: model persistence for all scenarios ( #21051 )
2026-03-04 03:28:12 +00:00
28af4e127f
fix: merge duplicate imports in packages/core (3/4) ( #20928 )
2026-03-04 00:12:59 +00:00
c332d1e636
feat(extensions): add support for plan directory in extension manifest ( #20354 )
...
Co-authored-by: Mahima Shanware <mshanware@google.com >
Co-authored-by: Jerop Kipruto <jerop@google.com >
2026-03-03 16:50:18 +00:00
d05ba11a31
refactor(core): replace manual syncPlanModeTools with declarative policy rules ( #20596 )
2026-03-02 22:30:50 +00:00
d7320f5425
refactor(core,cli): useAlternateBuffer read from config ( #20346 )
...
Co-authored-by: Jacob Richman <jacob314@gmail.com >
2026-02-27 15:55:02 +00:00
9b7852f11c
[Gemma x Gemini CLI] Add an Experimental Gemma Router that uses a LiteRT-LM shim into the Composite Model Classifier Strategy ( #17231 )
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Allen Hutchison <adh@google.com >
2026-02-26 23:43:43 +00:00
50947c57ce
fix(acp): update auth handshake to spec ( #19725 )
2026-02-25 15:04:42 +00:00
bf278ef2b0
feat(plan): support automatic model switching for Plan Mode ( #20240 )
2026-02-25 00:15:14 +00:00
d47d4855db
feat(hooks): adds support for RuntimeHook functions. ( #19598 )
2026-02-24 21:03:36 +00:00
9e95b8b3c5
feat(browser): implement experimental browser agent ( #19284 )
2026-02-24 17:22:09 +00:00
2ff7738b5d
Add new setting to configure maxRetries ( #20064 )
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-02-23 23:57:16 +00:00
ac04c388e0
Fix: Persist manual model selection on restart #19864 ( #19891 )
2026-02-23 03:44:00 +00:00
d96bd05d36
fix(core): allow any preview model in quota access check ( #19867 )
2026-02-22 12:53:24 +00:00
84666e1bbc
fix(plan): time share by approval mode dashboard reporting negative time shares ( #19847 )
2026-02-22 00:32:57 +00:00
acb7f577de
chore(lint): fix lint errors seen when running npm run lint ( #19844 )
2026-02-21 18:33:25 +00:00
5fd557347e
fix(plan): exclude EnterPlanMode tool from YOLO mode ( #19570 )
2026-02-20 01:53:12 +00:00
537e56ffae
feat(plan): support configuring custom plans storage directory ( #19577 )
2026-02-19 22:47:08 +00:00
55c628e967
feat(core): experimental in-progress steering hints (1 of 3) ( #19008 )
2026-02-17 22:59:33 +00:00
099aa9621c
fix(core): ensure sub-agents are registered regardless of tools.allowed ( #18870 )
2026-02-12 02:12:01 +00:00
6dae3a5402
Feature/quota visibility 16795 ( #18203 )
2026-02-10 02:53:10 +00:00
89d4556c45
feat(core): Render memory hierarchically in context. ( #18350 )
2026-02-10 02:01:59 +00:00
bce1caefd0
feat(cli): disable folder trust in headless mode ( #18407 )
2026-02-09 23:46:49 +00:00
375c104b32
fix(core): ensure enter_plan_mode tool registration respects experimental.plan ( #18587 )
2026-02-09 01:57:01 +00:00
28805a4b2d
refactor: simplify tool output truncation to single config ( #18446 )
2026-02-06 21:41:19 +00:00
61d92c4a21
Remove previewFeatures and default to Gemini 3 ( #18414 )
2026-02-06 18:02:57 +00:00
bce57ca1af
feat(plan): fix invalid tool calls in plan mode ( #18352 )
2026-02-05 20:04:03 +00:00
94f4e5cc15
feat(core): enable getUserTierName in config ( #18265 )
2026-02-04 03:28:58 +00:00
7f066fd3a7
feat(cli): Display user identity (auth, email, tier) on startup ( #17591 )
...
Co-authored-by: Keith Guerin <keithguerin@gmail.com >
Co-authored-by: Yuna Seol <yunaseol@google.com >
2026-01-29 05:07:52 +00:00
adc8e11bb1
Add support for an additional exclusion file besides .gitignore and .geminiignore ( #16487 )
...
Co-authored-by: Adam Weidman <adamfweidman@google.com >
2026-01-28 01:19:13 +00:00
49c26b4801
feat(plan): refresh system prompt when approval mode changes (Shift+Tab) ( #17585 )
2026-01-26 23:45:24 +00:00
13bc5f620c
feat(plan): add persistent plan file storage ( #17563 )
2026-01-26 21:57:27 +00:00
4fc3ebb930
fix(core): await MCP initialization in non-interactive mode ( #17390 )
2026-01-23 17:21:47 +00:00
2c6781d134
Refactor subagent delegation to be one tool per agent ( #17346 )
2026-01-23 02:18:31 +00:00
62dd9b5b3c
feat(core): Remove legacy settings. ( #17244 )
2026-01-22 20:59:47 +00:00
3cca8ec0f0
feat(config): default enableEventDrivenScheduler to true ( #17211 )
2026-01-21 22:40:19 +00:00
211d2c5fdd
feat(core): Ensure all properties in hooks object are event names. ( #16870 )
2026-01-20 22:47:31 +00:00
451e0b49cb
feat(cli): add experiment gate for event-driven scheduler ( #17055 )
2026-01-20 03:59:30 +00:00
1998a713e2
fix(hooks): enable /hooks disable to reliably stop single hooks ( #16804 )
2026-01-17 00:28:36 +00:00
1e8f87fbdf
Add support for running available commands prior to MCP servers loading ( #15596 )
2026-01-15 20:33:16 +00:00
5bdfe1a1fa
feat(plan): add experimental plan flag ( #16650 )
2026-01-15 00:55:10 +00:00
bb6c574144
feat(admin): support admin-enforced settings for Agent Skills ( #16406 )
2026-01-14 07:40:23 +00:00
3b678a4da0
fix(core): avoid 'activate_skill' re-registration warning ( #16398 )
2026-01-12 19:31:34 +00:00
465ec9759d
fix(core): ensure sub-agent schema and prompt refresh during runtime ( #16409 )
...
Co-authored-by: Sehoon Shon <sshon@google.com >
2026-01-12 17:11:24 +00:00
ca48661423
feat(core): add local experiments override via GEMINI_EXP ( #16181 )
2026-01-09 18:47:05 +00:00
1aa35c8796
enable cli_help agent by default ( #16100 )
2026-01-07 23:43:12 +00:00
2cb33b2f76
Agent Skills: Implement /skills reload ( #15865 )
2026-01-05 23:12:51 +00:00
e5d183031a
Opt-in to persist model from /model ( #15820 )
2026-01-05 20:31:13 +00:00
Sandy Tao