Sandy Tao
5194cef9c1
feat: add Forever Mode for autonomous long-running agent sessions
...
Add --forever CLI flag that enables autonomous agent operation with
auto-resume, context management, and session optimization.
Core features:
- schedule_work tool: agent declares pause duration, system auto-resumes
with countdown timer
- PreCompress hook enhancement: hooks can return newHistory to replace
built-in LLM compression
- Idle hook: fires after configurable inactivity, can auto-submit prompts
- Forever mode disables MemoryTool, EnterPlanModeTool, interactive shell
Session optimization for long-running sessions:
- Record lastCompressionIndex on ConversationRecord; on resume, only load
post-compression messages (O(N) → O(recent))
- Skip file I/O in updateMessagesFromHistory when no tool results to sync
- Prune UI history to last 50 items after each context compression to
prevent unbounded memory growth
2026-03-17 14:33:58 -07:00
Dmitry Lyalin
7f8ce8657c
Add low/full CLI error verbosity mode for cleaner UI ( #20399 )
2026-02-27 19:15:10 +00:00
Gaurav
b2d6844f9b
feat(billing): implement G1 AI credits overage flow with billing telemetry ( #18590 )
2026-02-27 18:15:06 +00:00
Sehoon Shon
edb1fdea30
fix(cli): support quota error fallbacks for all authentication types ( #20475 )
...
Co-authored-by: Gal Zahavi <38544478+galz10@users.noreply.github.com >
2026-02-26 22:39:25 +00:00
Sehoon Shon
f97b04cc9a
feat(models): support Gemini 3.1 Pro Preview and fixes ( #19676 )
2026-02-20 19:19:21 +00:00
Sehoon Shon
15ef1cd797
feat(cli): handle invalid model names in useQuotaAndFallback ( #19222 )
2026-02-16 19:55:17 +00:00
Spencer
6dae3a5402
Feature/quota visibility 16795 ( #18203 )
2026-02-10 02:53:10 +00:00
Sehoon Shon
61d92c4a21
Remove previewFeatures and default to Gemini 3 ( #18414 )
2026-02-06 18:02:57 +00:00
Gaurav
5fe328c56a
Improve error messages on failed onboarding ( #17357 )
2026-01-26 14:31:19 +00:00
Gaurav
3b626e7c61
Add interactive ValidationDialog for handling 403 VALIDATION_REQUIRED errors. ( #16231 )
2026-01-21 00:23:01 +00:00
Adam Weidman
e34f0b4a98
fix: update currentSequenceModel when modelChanged ( #17051 )
2026-01-20 06:25:15 +00:00
N. Taylor Mullen
461c277bf2
Support for Built-in Agent Skills ( #16045 )
2026-01-10 06:26:58 +00:00
Christian Gunderman
c87d1aed4c
Fix an issue where the agent stops prematurely ( #16269 )
2026-01-09 23:05:27 +00:00
Sehoon Shon
69fc75c0b2
do not persist the fallback model ( #15483 )
2025-12-26 16:08:44 +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
7f2d33458a
Disallow unnecessary awaits. ( #15172 )
2025-12-17 05:28:18 +00:00
Sehoon Shon
d8a3d08f8e
fallback to flash for TerminalQuota errors ( #13791 )
2025-11-25 21:17:22 +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
Adam Weidman
1e42fdf6c2
fix(cli): handle flash model errors gracefully ( #12667 )
2025-11-06 22:13:38 +00:00
Sehoon Shon
31b34b11ab
Let users know when falling back to flash, and update the error messa… ( #12640 )
2025-11-06 18:43:21 +00:00
Jacob Richman
54fa26ef0e
Fix tests to wrap all calls changing the UI with act. ( #12268 )
2025-10-30 18:50:26 +00:00
Jacob Richman
13aa0148e7
Migrate tests to use avoid jsdom ( #12118 )
2025-10-28 17:32:15 +00:00
Jacob Richman
ee66732ad2
First batch of fixing tests to use best practices. ( #11964 )
2025-10-25 21:41:53 +00:00
Gaurav
ee92db7533
fix: handle request retries and model fallback correctly ( #11624 )
2025-10-24 18:09:06 +00:00
Gaurav
996c9f5955
Revert "fix: handle request retries and model fallback correctly" ( #11164 )
2025-10-14 23:30:59 +00:00
Gaurav
319f43fa23
fix: handle request retries and model fallback correctly ( #9407 )
2025-10-03 20:24:50 +00:00
Abhi
538e6cd19a
feat(routing): Initialize model routing architecture ( #8153 )
2025-09-11 17:38:50 +00:00
Abhi
f6f2fff724
refactor: Centralize and improve model fallback handling ( #7634 )
2025-09-08 20:19:52 +00:00