Refreshed bundled instructions for GPT-5.6 Sol, Terra, and Luna, and corrected their context windows to 272,000 tokens. (#33972, #34009) · #33972 Backport refreshed bundled model metadata to 0.144 @sayan-oai · #34009 Narrow 0.144 hotfix to GPT-5.6 prompts and context @sayan-oai
Run a 30-minute bake-off of OpenAI Codex CLI's new/default model on one real task you care about.
Compare default model quality/latency on your real tasks.
Changelog for v0.50.0-preview.1 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/28150 · Fix no_proxy test by @jerrylin3321 in https://github.com/google-gemini/gemini-cli/pull/28131 · chore(release): bump version to 0.51.0-nightly.20260625.g3fbf93e26 by @g
Run a 30-minute bake-off of Gemini CLI's new/default model on one real task you care about.
Read the primary release notes and note any permission, sandbox, or API breaks for Gemini CLI.
Try in a throwaway repo before changing daily workflow.
Changelog for v0.50.0-preview.1 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/28150 · Fix no_proxy test by @jerrylin3321 in https://github.com/google-gemini/gemini-cli/pull/28131 · chore(release): bump version to 0.51.0-nightly.20260625.g3fbf93e26 by @g
Run a 30-minute bake-off of Gemini CLI's new/default model on one real task you care about.
Read the primary release notes and note any permission, sandbox, or API breaks for Gemini CLI.
Try in a throwaway repo before changing daily workflow.
Improve Claude adaptive thinking handling across more response shapes. · Avoid OpenAI Responses phase handling that could break some conversations. · Preserve grep symlink paths in search results. (@remixz) · Preserve Mistral reasoning history across turns. · Stabilize Mistral pr
Re-check agent/tool permissions for OpenCode on a throwaway repo before daily use.
Read the primary release notes and note any permission, sandbox, or API breaks for OpenCode.
Try in a throwaway repo before changing daily workflow.
Add a ClinePass limit-reached error with a one-click option to switch to Cline usage-based billing. · Allow selecting Cline free models on the ClinePass provider, organized into Subscribed and Free tabs with model descriptions. · Refine ClinePass onboarding and provider settings
Run a 30-minute bake-off of Cline's new/default model on one real task you care about.
Read the primary release notes and note any permission, sandbox, or API breaks for Cline.
Verify plan/credit impact for Cline before expanding usage.
You can now select Cline free models on the ClinePass provider in the model picker · Removed the retired ClinePass GLM 5.1 model · Fixed OpenAI Codex model metadata under the GPT Subscription provider · `str_replace` edits now report accurate diffs · Fixed context compaction so c
Run a 30-minute bake-off of Cline's new/default model on one real task you care about.
Read the primary release notes and note any permission, sandbox, or API breaks for Cline.
Verify plan/credit impact for Cline before expanding usage.
Community signal · 0 approved · 0 deferred · 0 ignored
Anonymous public tally (one vote per visitor; changing choice updates your vote). Not moderated product truth.
High-signal releases
Claude Codev2.1.212High impact7/17/2026, 12:26:27 AM
v2.1.212
`/fork` now copies your conversation into a new background session (its own row in `claude agents`) while you keep working; the in-session subagent it used to launch is now `/subtask` · Added `claude auto-mode reset` to restore the default auto-mode configuration, with a confirmation prompt (pass `--yes` to skip) · Added a session-wide limit on WebSearch tool calls (default 200, tunable via `CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION`) to stop runaway search loops · Added a per-session cap on suba
Improved branch filtering with all, local, and remote options in the branch picker. ([#60857](https://github.com/zed-industries/zed/pull/60857); thanks [chirivelli](https://github.com/chirivelli)) · Settings UI: Improved support for window widths below 900 px. ([#60786](https://github.com/zed-industries/zed/pull/60786); thanks [feitreim](https://github.com/feitreim)) · Improved semantic token highlighting to distinguish function parameters from local variables. ([#60949](https://github.com/zed-i
Arbitrary command execution in goose CLI via `goose review` (via git core.fsmonitor config) - [GHSA-r5pp-p5r8-466r](https://github.com/aaif-goose/goose/security/advisories/GHSA-r5pp-p5r8-466r) (credit to @0xmagic0) · Support for latest Gemini models [#10630](https://github.com/aaif-goose/goose/pull/10630) · Pass working_dir to the Stop hook context [#10296](https://github.com/aaif-goose/goose/pull/10296) · Declarative Sakana AI provider for OpenAI-compatible Fugu API [#10357](https://github.com/
Agent execution mode cycling is now publicly available: `default` -> `accept-edits` -> `plan`) · Added `request-review` (default) mode as the default execution behavior: automatically pauses before file write operations to display an interactive, line-level diff preview (`f` shortcut) where users can review, accept, or reject individual code modifications before they are saved to disk. · Added an `Agent Mode` option to the `/settings` panel so users can set and persist a default execution mode (
You can now select Cline free models on the ClinePass provider in the model picker · Removed the retired ClinePass GLM 5.1 model · Fixed OpenAI Codex model metadata under the GPT Subscription provider · `str_replace` edits now report accurate diffs · Fixed context compaction so canonical session history is preserved
Add a ClinePass limit-reached error with a one-click option to switch to Cline usage-based billing. · Allow selecting Cline free models on the ClinePass provider, organized into Subscribed and Free tabs with model descriptions. · Refine ClinePass onboarding and provider settings copy, and open the "learn more" link via the in-app URL handler. · Remove the Cline model picker recommendation copy. · Remove all references to GLM 5.1.
Improve Claude adaptive thinking handling across more response shapes. · Avoid OpenAI Responses phase handling that could break some conversations. · Preserve grep symlink paths in search results. (@remixz) · Preserve Mistral reasoning history across turns. · Stabilize Mistral prompt caching.
Changelog for v0.50.0-preview.1 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/28150 · Fix no_proxy test by @jerrylin3321 in https://github.com/google-gemini/gemini-cli/pull/28131 · chore(release): bump version to 0.51.0-nightly.20260625.g3fbf93e26 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/28151 · Vertex base url update by @DavidAPierce in https://github.com/google-gemini/gemini-cli/pull/28145 · fix(security): enforce case-insensitive sens
Changelog for v0.50.0-preview.1 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/28150 · Fix no_proxy test by @jerrylin3321 in https://github.com/google-gemini/gemini-cli/pull/28131 · chore(release): bump version to 0.51.0-nightly.20260625.g3fbf93e26 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/28151 · Vertex base url update by @DavidAPierce in https://github.com/google-gemini/gemini-cli/pull/28145 · fix(security): enforce case-insensitive sens
fix(sandbox): make ~/.gitconfig read-only in the macOS sandbox by @ompatel-aiml in https://github.com/google-gemini/gemini-cli/pull/28221 · fix(core): preserve escape sequences in string literals for modern models by @luisfelipe-alt in https://github.com/google-gemini/gemini-cli/pull/28299 · **Full Changelog**: https://github.com/google-gemini/gemini-cli/compare/v0.51.0-nightly.20260706.gf7af4e518...v0.51.0-nightly.20260707.g15a9429b6
Clinesdk/sdk/v0.0.65High impact7/19/2026, 4:02:15 AM
sdk/sdk/v0.0.65 SDK v0.0.65
Claude Code and Codex provider SDKs are now optional peer dependencies loaded on demand, dramatically cutting install size · Added Kimi K3 to the bundled ClinePass model fallback · Runs now retry once after refreshing expired OAuth credentials · Team runs: the spawn tool is no longer exposed to teammate agents · Team runs: errored teammate runs now report as failed instead of completed