@google/gemini-cli-core 0.43.0-preview.0 → 0.44.0-nightly.20260514.g77078b3e8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/docs/changelogs/index.md +16 -0
- package/dist/docs/changelogs/latest.md +259 -106
- package/dist/docs/changelogs/preview.md +178 -227
- package/dist/docs/cli/auto-memory.md +4 -5
- package/dist/docs/cli/gemini-md.md +0 -2
- package/dist/docs/cli/plan-mode.md +0 -1
- package/dist/docs/cli/settings.md +18 -19
- package/dist/docs/cli/tutorials/memory-management.md +2 -2
- package/dist/docs/reference/commands.md +0 -3
- package/dist/docs/reference/configuration.md +52 -62
- package/dist/docs/reference/tools.md +0 -2
- package/dist/docs/tools/memory.md +10 -13
- package/dist/google-gemini-cli-core-0.44.0-nightly.20260512.g022e8baef.tgz +0 -0
- package/dist/src/agents/agentLoader.d.ts +18 -18
- package/dist/src/agents/local-executor.js +7 -13
- package/dist/src/agents/local-executor.js.map +1 -1
- package/dist/src/agents/local-executor.test.js +7 -32
- package/dist/src/agents/local-executor.test.js.map +1 -1
- package/dist/src/agents/registry.js +28 -21
- package/dist/src/agents/registry.js.map +1 -1
- package/dist/src/agents/registry.test.js +8 -18
- package/dist/src/agents/registry.test.js.map +1 -1
- package/dist/src/availability/autoRoutingFallback.integration.test.js +1 -0
- package/dist/src/availability/autoRoutingFallback.integration.test.js.map +1 -1
- package/dist/src/availability/fallbackIntegration.test.js +1 -0
- package/dist/src/availability/fallbackIntegration.test.js.map +1 -1
- package/dist/src/availability/policyHelpers.js +8 -12
- package/dist/src/availability/policyHelpers.js.map +1 -1
- package/dist/src/availability/policyHelpers.test.js +8 -1
- package/dist/src/availability/policyHelpers.test.js.map +1 -1
- package/dist/src/code_assist/oauth-credential-storage.js +3 -1
- package/dist/src/code_assist/oauth-credential-storage.js.map +1 -1
- package/dist/src/code_assist/oauth-credential-storage.test.js +25 -0
- package/dist/src/code_assist/oauth-credential-storage.test.js.map +1 -1
- package/dist/src/code_assist/oauth2.js +6 -2
- package/dist/src/code_assist/oauth2.js.map +1 -1
- package/dist/src/code_assist/setup.test.js +1 -0
- package/dist/src/code_assist/setup.test.js.map +1 -1
- package/dist/src/commands/memory.d.ts +1 -2
- package/dist/src/commands/memory.js +3 -27
- package/dist/src/commands/memory.js.map +1 -1
- package/dist/src/commands/memory.test.js +12 -58
- package/dist/src/commands/memory.test.js.map +1 -1
- package/dist/src/config/config.d.ts +33 -21
- package/dist/src/config/config.js +63 -51
- package/dist/src/config/config.js.map +1 -1
- package/dist/src/config/config.test.js +41 -87
- package/dist/src/config/config.test.js.map +1 -1
- package/dist/src/config/defaultModelConfigs.js +36 -32
- package/dist/src/config/defaultModelConfigs.js.map +1 -1
- package/dist/src/config/models.d.ts +8 -3
- package/dist/src/config/models.js +34 -9
- package/dist/src/config/models.js.map +1 -1
- package/dist/src/config/projectRegistry.js +1 -1
- package/dist/src/config/projectRegistry.js.map +1 -1
- package/dist/src/context/processors/toolMaskingProcessor.js +1 -2
- package/dist/src/context/processors/toolMaskingProcessor.js.map +1 -1
- package/dist/src/context/toolOutputMaskingService.js +1 -2
- package/dist/src/context/toolOutputMaskingService.js.map +1 -1
- package/dist/src/context/toolOutputMaskingService.test.js +5 -20
- package/dist/src/context/toolOutputMaskingService.test.js.map +1 -1
- package/dist/src/core/baseLlmClient.js +6 -2
- package/dist/src/core/baseLlmClient.js.map +1 -1
- package/dist/src/core/client.test.js +1 -11
- package/dist/src/core/client.test.js.map +1 -1
- package/dist/src/core/fakeContentGenerator.js +12 -4
- package/dist/src/core/fakeContentGenerator.js.map +1 -1
- package/dist/src/core/localLiteRtLmClient.js +6 -2
- package/dist/src/core/localLiteRtLmClient.js.map +1 -1
- package/dist/src/core/prompts.test.js +7 -2
- package/dist/src/core/prompts.test.js.map +1 -1
- package/dist/src/fallback/handler.js +6 -1
- package/dist/src/fallback/handler.js.map +1 -1
- package/dist/src/fallback/handler.test.js +2 -0
- package/dist/src/fallback/handler.test.js.map +1 -1
- package/dist/src/generated/git-commit.d.ts +2 -2
- package/dist/src/generated/git-commit.js +2 -2
- package/dist/src/generated/git-commit.js.map +1 -1
- package/dist/src/ide/ide-client.js +5 -3
- package/dist/src/ide/ide-client.js.map +1 -1
- package/dist/src/ide/ide-connection-utils.js +12 -10
- package/dist/src/ide/ide-connection-utils.js.map +1 -1
- package/dist/src/ide/types.d.ts +16 -16
- package/dist/src/mcp/oauth-provider.d.ts +7 -0
- package/dist/src/mcp/oauth-provider.js +41 -0
- package/dist/src/mcp/oauth-provider.js.map +1 -1
- package/dist/src/mcp/oauth-token-storage.js +7 -1
- package/dist/src/mcp/oauth-token-storage.js.map +1 -1
- package/dist/src/mcp/oauth-token-storage.test.js +55 -0
- package/dist/src/mcp/oauth-token-storage.test.js.map +1 -1
- package/dist/src/mcp/stored-token-provider.d.ts +27 -0
- package/dist/src/mcp/stored-token-provider.js +76 -0
- package/dist/src/mcp/stored-token-provider.js.map +1 -0
- package/dist/src/mcp/token-storage/keychain-token-storage.js +2 -2
- package/dist/src/mcp/token-storage/keychain-token-storage.js.map +1 -1
- package/dist/src/mcp/token-storage/keychain-token-storage.test.js +14 -1
- package/dist/src/mcp/token-storage/keychain-token-storage.test.js.map +1 -1
- package/dist/src/policy/core-tools-mapping.test.js +9 -1
- package/dist/src/policy/core-tools-mapping.test.js.map +1 -1
- package/dist/src/policy/policies/plan.toml +1 -1
- package/dist/src/policy/policies/write.toml +0 -7
- package/dist/src/policy/policy-engine.test.js +0 -8
- package/dist/src/policy/policy-engine.test.js.map +1 -1
- package/dist/src/policy/sandboxPolicyManager.d.ts +20 -20
- package/dist/src/prompts/promptProvider.js +5 -7
- package/dist/src/prompts/promptProvider.js.map +1 -1
- package/dist/src/prompts/promptProvider.test.js +3 -1
- package/dist/src/prompts/promptProvider.test.js.map +1 -1
- package/dist/src/prompts/{snippets-memory-v2.test.js → snippets-memory.test.js} +5 -23
- package/dist/src/prompts/snippets-memory.test.js.map +1 -0
- package/dist/src/prompts/snippets.d.ts +4 -11
- package/dist/src/prompts/snippets.js +11 -22
- package/dist/src/prompts/snippets.js.map +1 -1
- package/dist/src/prompts/snippets.legacy.d.ts +0 -1
- package/dist/src/prompts/snippets.legacy.js +5 -13
- package/dist/src/prompts/snippets.legacy.js.map +1 -1
- package/dist/src/sandbox/utils/commandSafety.js +22 -2
- package/dist/src/sandbox/utils/commandSafety.js.map +1 -1
- package/dist/src/sandbox/utils/commandSafety.test.js +85 -0
- package/dist/src/sandbox/utils/commandSafety.test.js.map +1 -0
- package/dist/src/services/modelConfigService.d.ts +2 -0
- package/dist/src/services/modelConfigService.js +19 -9
- package/dist/src/services/modelConfigService.js.map +1 -1
- package/dist/src/services/trackerTypes.d.ts +4 -4
- package/dist/src/tools/definitions/base-declarations.d.ts +0 -3
- package/dist/src/tools/definitions/base-declarations.js +0 -4
- package/dist/src/tools/definitions/base-declarations.js.map +1 -1
- package/dist/src/tools/definitions/coreTools.d.ts +1 -2
- package/dist/src/tools/definitions/coreTools.js +2 -8
- package/dist/src/tools/definitions/coreTools.js.map +1 -1
- package/dist/src/tools/definitions/coreToolsModelSnapshots.test.js +1 -2
- package/dist/src/tools/definitions/coreToolsModelSnapshots.test.js.map +1 -1
- package/dist/src/tools/definitions/model-family-sets/default-legacy.js +2 -29
- package/dist/src/tools/definitions/model-family-sets/default-legacy.js.map +1 -1
- package/dist/src/tools/definitions/model-family-sets/gemini-3.js +2 -22
- package/dist/src/tools/definitions/model-family-sets/gemini-3.js.map +1 -1
- package/dist/src/tools/definitions/types.d.ts +0 -1
- package/dist/src/tools/jit-context.d.ts +1 -1
- package/dist/src/tools/jit-context.js +1 -4
- package/dist/src/tools/jit-context.js.map +1 -1
- package/dist/src/tools/jit-context.test.js +1 -13
- package/dist/src/tools/jit-context.test.js.map +1 -1
- package/dist/src/tools/mcp-client.js +18 -21
- package/dist/src/tools/mcp-client.js.map +1 -1
- package/dist/src/tools/mcp-client.test.js +153 -14
- package/dist/src/tools/mcp-client.test.js.map +1 -1
- package/dist/src/tools/memoryTool.d.ts +9 -31
- package/dist/src/tools/memoryTool.js +47 -262
- package/dist/src/tools/memoryTool.js.map +1 -1
- package/dist/src/tools/memoryTool.test.js +41 -312
- package/dist/src/tools/memoryTool.test.js.map +1 -1
- package/dist/src/tools/ripGrep.d.ts +3 -7
- package/dist/src/tools/ripGrep.js +40 -34
- package/dist/src/tools/ripGrep.js.map +1 -1
- package/dist/src/tools/ripGrep.test.js +162 -276
- package/dist/src/tools/ripGrep.test.js.map +1 -1
- package/dist/src/tools/shell.d.ts +1 -0
- package/dist/src/tools/shell.js +82 -8
- package/dist/src/tools/shell.js.map +1 -1
- package/dist/src/tools/shell.test.js +138 -1
- package/dist/src/tools/shell.test.js.map +1 -1
- package/dist/src/tools/tool-names.d.ts +3 -3
- package/dist/src/tools/tool-names.js +4 -5
- package/dist/src/tools/tool-names.js.map +1 -1
- package/dist/src/utils/environmentContext.js +1 -6
- package/dist/src/utils/environmentContext.js.map +1 -1
- package/dist/src/utils/environmentContext.test.js +4 -14
- package/dist/src/utils/environmentContext.test.js.map +1 -1
- package/dist/src/utils/extensionLoader.js +2 -2
- package/dist/src/utils/extensionLoader.js.map +1 -1
- package/dist/src/utils/extensionLoader.test.js +22 -15
- package/dist/src/utils/extensionLoader.test.js.map +1 -1
- package/dist/src/utils/filesearch/fileSearch.js +20 -9
- package/dist/src/utils/filesearch/fileSearch.js.map +1 -1
- package/dist/src/utils/memoryDiscovery.d.ts +0 -20
- package/dist/src/utils/memoryDiscovery.js +0 -189
- package/dist/src/utils/memoryDiscovery.js.map +1 -1
- package/dist/src/utils/memoryDiscovery.test.js +32 -440
- package/dist/src/utils/memoryDiscovery.test.js.map +1 -1
- package/dist/src/utils/paths.d.ts +4 -0
- package/dist/src/utils/paths.js +36 -0
- package/dist/src/utils/paths.js.map +1 -1
- package/dist/src/utils/paths.test.js +41 -1
- package/dist/src/utils/paths.test.js.map +1 -1
- package/dist/src/utils/safeJsonStringify.js +0 -2
- package/dist/src/utils/safeJsonStringify.js.map +1 -1
- package/dist/tsconfig.tsbuildinfo +1 -1
- package/package.json +1 -1
- package/dist/src/policy/memory-manager-policy.test.js +0 -80
- package/dist/src/policy/memory-manager-policy.test.js.map +0 -1
- package/dist/src/policy/policies/memory-manager.toml +0 -20
- package/dist/src/prompts/snippets-memory-v2.test.js.map +0 -1
- /package/dist/src/{policy/memory-manager-policy.test.d.ts → prompts/snippets-memory.test.d.ts} +0 -0
- /package/dist/src/{prompts/snippets-memory-v2.test.d.ts → sandbox/utils/commandSafety.test.d.ts} +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
|
-
# Preview release: v0.
|
|
1
|
+
# Preview release: v0.43.0-preview.0
|
|
2
2
|
|
|
3
|
-
Released: May
|
|
3
|
+
Released: May 12, 2026
|
|
4
4
|
|
|
5
5
|
Our preview release includes the latest, new, and experimental features. This
|
|
6
6
|
release may not be as stable as our [latest weekly release](latest.md).
|
|
@@ -13,233 +13,184 @@ npm install -g @google/gemini-cli@preview
|
|
|
13
13
|
|
|
14
14
|
## Highlights
|
|
15
15
|
|
|
16
|
-
- **
|
|
17
|
-
|
|
18
|
-
- **
|
|
19
|
-
|
|
20
|
-
- **
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
automatic retries for stream errors, and better handling of invalid stream
|
|
27
|
-
events.
|
|
16
|
+
- **Surgical Code Edits:** Steer models to use the `edit` tool for precise code
|
|
17
|
+
modifications, improving accuracy and reducing context usage.
|
|
18
|
+
- **Session Portability:** Added ability to export chat sessions to files and
|
|
19
|
+
import them via a new CLI flag, enabling session persistence and sharing.
|
|
20
|
+
- **Enhanced Security:** Introduced comprehensive shell command safety
|
|
21
|
+
evaluations and strengthened model steering to prevent unauthorized changes.
|
|
22
|
+
- **Context Management:** Implemented a new adaptive token calculator for more
|
|
23
|
+
accurate content size estimations and optimized context pipelines.
|
|
24
|
+
- **UX Improvements:** Enhanced tool call visibility with prefixed IDs and
|
|
25
|
+
improved the UI for session resumption and MCP list management.
|
|
28
26
|
|
|
29
27
|
## What's Changed
|
|
30
28
|
|
|
31
|
-
-
|
|
32
|
-
[#
|
|
33
|
-
-
|
|
34
|
-
[#
|
|
35
|
-
- fix(
|
|
36
|
-
|
|
37
|
-
- fix(
|
|
38
|
-
[#
|
|
39
|
-
-
|
|
40
|
-
[#
|
|
41
|
-
-
|
|
42
|
-
[#
|
|
43
|
-
- fix(core):
|
|
44
|
-
[#
|
|
45
|
-
-
|
|
46
|
-
[#
|
|
47
|
-
-
|
|
48
|
-
[#
|
|
49
|
-
-
|
|
50
|
-
[#
|
|
51
|
-
- fix(
|
|
52
|
-
[#
|
|
53
|
-
-
|
|
54
|
-
[#
|
|
55
|
-
-
|
|
56
|
-
[#
|
|
57
|
-
-
|
|
58
|
-
[#
|
|
59
|
-
-
|
|
60
|
-
[#
|
|
61
|
-
- fix(
|
|
62
|
-
|
|
63
|
-
- fix(
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
-
|
|
71
|
-
|
|
72
|
-
-
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
-
|
|
78
|
-
[#
|
|
79
|
-
-
|
|
80
|
-
|
|
81
|
-
-
|
|
82
|
-
|
|
83
|
-
-
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
-
|
|
88
|
-
|
|
89
|
-
-
|
|
90
|
-
|
|
91
|
-
-
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
|
|
95
|
-
-
|
|
96
|
-
|
|
97
|
-
-
|
|
98
|
-
|
|
99
|
-
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
-
|
|
104
|
-
|
|
105
|
-
-
|
|
106
|
-
|
|
107
|
-
-
|
|
108
|
-
|
|
109
|
-
-
|
|
110
|
-
|
|
111
|
-
-
|
|
112
|
-
|
|
113
|
-
-
|
|
114
|
-
|
|
115
|
-
-
|
|
116
|
-
|
|
117
|
-
|
|
118
|
-
[#
|
|
119
|
-
- fix:
|
|
120
|
-
[#
|
|
121
|
-
- feat(
|
|
122
|
-
[#
|
|
123
|
-
- fix(
|
|
124
|
-
[#
|
|
125
|
-
-
|
|
126
|
-
[#
|
|
127
|
-
-
|
|
128
|
-
|
|
129
|
-
|
|
130
|
-
-
|
|
131
|
-
[#
|
|
132
|
-
-
|
|
133
|
-
[#
|
|
134
|
-
-
|
|
135
|
-
[#
|
|
136
|
-
-
|
|
137
|
-
|
|
138
|
-
-
|
|
139
|
-
[#
|
|
140
|
-
- fix(cli):
|
|
141
|
-
[#
|
|
142
|
-
- fix(
|
|
143
|
-
|
|
144
|
-
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
|
|
148
|
-
|
|
149
|
-
[#
|
|
150
|
-
- fix(core):
|
|
151
|
-
[#
|
|
152
|
-
-
|
|
153
|
-
[#
|
|
154
|
-
- fix
|
|
155
|
-
[#
|
|
156
|
-
-
|
|
157
|
-
[#
|
|
158
|
-
-
|
|
159
|
-
[#
|
|
160
|
-
-
|
|
161
|
-
|
|
162
|
-
-
|
|
163
|
-
|
|
164
|
-
|
|
165
|
-
-
|
|
166
|
-
|
|
167
|
-
-
|
|
168
|
-
|
|
169
|
-
-
|
|
170
|
-
|
|
171
|
-
|
|
172
|
-
[#
|
|
173
|
-
-
|
|
174
|
-
[#
|
|
175
|
-
-
|
|
176
|
-
[#
|
|
177
|
-
-
|
|
178
|
-
[#
|
|
179
|
-
-
|
|
180
|
-
[#
|
|
181
|
-
-
|
|
182
|
-
|
|
183
|
-
-
|
|
184
|
-
|
|
185
|
-
-
|
|
186
|
-
|
|
187
|
-
-
|
|
188
|
-
|
|
189
|
-
-
|
|
190
|
-
|
|
191
|
-
-
|
|
192
|
-
|
|
193
|
-
-
|
|
194
|
-
|
|
195
|
-
-
|
|
196
|
-
[#26453](https://github.com/google-gemini/gemini-cli/pull/26453)
|
|
197
|
-
- fix(cli)#21297: clear skills consent dialog before reload in
|
|
198
|
-
[#26431](https://github.com/google-gemini/gemini-cli/pull/26431)
|
|
199
|
-
- fix(cli): render LaTeX-style output as Unicode in the TUI in
|
|
200
|
-
[#25802](https://github.com/google-gemini/gemini-cli/pull/25802)
|
|
201
|
-
- fix(core): use close event instead of exit in child_process fallback in
|
|
202
|
-
[#25695](https://github.com/google-gemini/gemini-cli/pull/25695)
|
|
203
|
-
- feat(voice): add privacy and compliance UX warning for Gemini Live backend in
|
|
204
|
-
[#26454](https://github.com/google-gemini/gemini-cli/pull/26454)
|
|
205
|
-
- feat(memory): add Auto Memory inbox flow with canonical-patch contract in
|
|
206
|
-
[#26338](https://github.com/google-gemini/gemini-cli/pull/26338)
|
|
207
|
-
- test(cleanup): fix temporary directory leaks in test suites in
|
|
208
|
-
[#26217](https://github.com/google-gemini/gemini-cli/pull/26217)
|
|
209
|
-
- feat: add ignoreLocalEnv setting and --ignore-env flag (#2493) in
|
|
210
|
-
[#26445](https://github.com/google-gemini/gemini-cli/pull/26445)
|
|
211
|
-
- docs(sdk): add JSDoc to all exported interfaces and types in
|
|
212
|
-
[#26277](https://github.com/google-gemini/gemini-cli/pull/26277)
|
|
213
|
-
- feat(cli): improve /agents refresh logging in
|
|
214
|
-
[#26442](https://github.com/google-gemini/gemini-cli/pull/26442)
|
|
215
|
-
- Fix: make Dockerfile self-contained with multi-stage build in
|
|
216
|
-
[#24277](https://github.com/google-gemini/gemini-cli/pull/24277)
|
|
217
|
-
- fix(core): filter unsupported multimodal types from tool responses in
|
|
218
|
-
[#26352](https://github.com/google-gemini/gemini-cli/pull/26352)
|
|
219
|
-
- fix(core): properly format markdown in AskUser tool by unescaping newlines in
|
|
220
|
-
[#26349](https://github.com/google-gemini/gemini-cli/pull/26349)
|
|
221
|
-
- feat(bot): add actions spend metric script in
|
|
222
|
-
[#26463](https://github.com/google-gemini/gemini-cli/pull/26463)
|
|
223
|
-
- feat(cli): add /bug-memory command and auto-capture heap snapshot in /bug in
|
|
224
|
-
[#25639](https://github.com/google-gemini/gemini-cli/pull/25639)
|
|
225
|
-
- fix(cli): make SkillInboxDialog fit and scroll in alternate buffer in
|
|
226
|
-
[#26455](https://github.com/google-gemini/gemini-cli/pull/26455)
|
|
227
|
-
- Robust Scale-Safe Lifecycle Consolidation in
|
|
228
|
-
[#26355](https://github.com/google-gemini/gemini-cli/pull/26355)
|
|
229
|
-
- fix(ci): respect exempt labels when closing stale items in
|
|
230
|
-
[#26475](https://github.com/google-gemini/gemini-cli/pull/26475)
|
|
231
|
-
- fix(cli): use os.homedir() for home directory warning check in
|
|
232
|
-
[#25890](https://github.com/google-gemini/gemini-cli/pull/25890)
|
|
233
|
-
- fix(a2a-server): resolve tool approval race condition and improve status
|
|
234
|
-
reporting in [#26479](https://github.com/google-gemini/gemini-cli/pull/26479)
|
|
235
|
-
- fix(cli): prevent settings dialog border clipping using maxHeight in
|
|
236
|
-
[#26507](https://github.com/google-gemini/gemini-cli/pull/26507)
|
|
237
|
-
- feat: allow queuing messages during compression (#24071) in
|
|
238
|
-
[#26506](https://github.com/google-gemini/gemini-cli/pull/26506)
|
|
239
|
-
- fix(core): retry on ERR_STREAM_PREMATURE_CLOSE errors in
|
|
240
|
-
[#26519](https://github.com/google-gemini/gemini-cli/pull/26519)
|
|
241
|
-
- fix(core): Minor fixes for generalist profile. in
|
|
242
|
-
[#26357](https://github.com/google-gemini/gemini-cli/pull/26357)
|
|
29
|
+
- feat(core): steer model to use edit tool for surgical edits, fix a typo in
|
|
30
|
+
[#26480](https://github.com/google-gemini/gemini-cli/pull/26480)
|
|
31
|
+
- docs: clarify Auto Memory proposes memory updates and skills in
|
|
32
|
+
[#26527](https://github.com/google-gemini/gemini-cli/pull/26527)
|
|
33
|
+
- fix(core): reject numeric project IDs in GOOGLE_CLOUD_PROJECT (#24695) in
|
|
34
|
+
[#26532](https://github.com/google-gemini/gemini-cli/pull/26532)
|
|
35
|
+
- fix(core): remove unsafe type assertion suppressions in error utils in
|
|
36
|
+
[#19881](https://github.com/google-gemini/gemini-cli/pull/19881)
|
|
37
|
+
- fix(core): allow redirection in YOLO and AUTO_EDIT modes without sandboxing in
|
|
38
|
+
[#26542](https://github.com/google-gemini/gemini-cli/pull/26542)
|
|
39
|
+
- ci(release): build and attach unsigned macOS binaries to releases in
|
|
40
|
+
[#26462](https://github.com/google-gemini/gemini-cli/pull/26462)
|
|
41
|
+
- fix(core): Fix chat corruption bug in context manager. in
|
|
42
|
+
[#26534](https://github.com/google-gemini/gemini-cli/pull/26534)
|
|
43
|
+
- fix(cli): provide JSON output for AgentExecutionStopped in non-interactive
|
|
44
|
+
mode in [#26504](https://github.com/google-gemini/gemini-cli/pull/26504)
|
|
45
|
+
- feat(evals): add shell command safety evals in
|
|
46
|
+
[#26528](https://github.com/google-gemini/gemini-cli/pull/26528)
|
|
47
|
+
- fix(core): handle invalid custom plans directory gracefully in
|
|
48
|
+
[#26560](https://github.com/google-gemini/gemini-cli/pull/26560)
|
|
49
|
+
- fix(acp): move tool explanation from thought stream to tool call content in
|
|
50
|
+
[#26554](https://github.com/google-gemini/gemini-cli/pull/26554)
|
|
51
|
+
- fix(a2a-server): Resolve race condition in tool completion waiting in
|
|
52
|
+
[#26568](https://github.com/google-gemini/gemini-cli/pull/26568)
|
|
53
|
+
- fix(cli): randomize sandbox container names in
|
|
54
|
+
[#26014](https://github.com/google-gemini/gemini-cli/pull/26014)
|
|
55
|
+
- fix(core): Fix hysteresis in async context management pipelines. in
|
|
56
|
+
[#26452](https://github.com/google-gemini/gemini-cli/pull/26452)
|
|
57
|
+
- Tighten private Auto Memory patch allowlist in
|
|
58
|
+
[#26535](https://github.com/google-gemini/gemini-cli/pull/26535)
|
|
59
|
+
- fix(cli): hide read-only settings scopes in
|
|
60
|
+
[#26249](https://github.com/google-gemini/gemini-cli/pull/26249)
|
|
61
|
+
- fix(ci): preserve executable bit for mac binaries in
|
|
62
|
+
[#26600](https://github.com/google-gemini/gemini-cli/pull/26600)
|
|
63
|
+
- fix(cli): improve mcp list UX in untrusted folders in
|
|
64
|
+
[#26457](https://github.com/google-gemini/gemini-cli/pull/26457)
|
|
65
|
+
- fix(core): prevent silent hang during OAuth auth on headless Linux in
|
|
66
|
+
[#26571](https://github.com/google-gemini/gemini-cli/pull/26571)
|
|
67
|
+
- Changelog for v0.42.0-preview.0 in
|
|
68
|
+
[#26537](https://github.com/google-gemini/gemini-cli/pull/26537)
|
|
69
|
+
- ci: fix Argument list too long in triage workflows in
|
|
70
|
+
[#26603](https://github.com/google-gemini/gemini-cli/pull/26603)
|
|
71
|
+
- refactor(cli): migrate core tools to native ToolDisplay property and fix UI
|
|
72
|
+
rendering in [#25186](https://github.com/google-gemini/gemini-cli/pull/25186)
|
|
73
|
+
- don't wrap args unnecessarily in
|
|
74
|
+
[#26599](https://github.com/google-gemini/gemini-cli/pull/26599)
|
|
75
|
+
- fix(core): preserve system PATH in Git environment to fix ENOENT (#25034) in
|
|
76
|
+
[#26587](https://github.com/google-gemini/gemini-cli/pull/26587)
|
|
77
|
+
- fix(routing): fix resolveClassifierModel argument mismatch in
|
|
78
|
+
ApprovalModeStrategy in
|
|
79
|
+
[#26658](https://github.com/google-gemini/gemini-cli/pull/26658)
|
|
80
|
+
- docs: add vi mode shortcuts and clarify MCP/custom sandbox setup in
|
|
81
|
+
[#23853](https://github.com/google-gemini/gemini-cli/pull/23853)
|
|
82
|
+
- fix(ux): fixed issue with transcribed text not showing after releasing space
|
|
83
|
+
in [#26609](https://github.com/google-gemini/gemini-cli/pull/26609)
|
|
84
|
+
- ci: fix json parsing in scheduled triage workflow in
|
|
85
|
+
[#26656](https://github.com/google-gemini/gemini-cli/pull/26656)
|
|
86
|
+
- fix(cli): hide /memory add subcommand when memoryV2 is enabled in
|
|
87
|
+
[#26605](https://github.com/google-gemini/gemini-cli/pull/26605)
|
|
88
|
+
- fix: prevent false command conflicts when launching from home directory in
|
|
89
|
+
[#23069](https://github.com/google-gemini/gemini-cli/pull/23069)
|
|
90
|
+
- fix(core): cache model routing decision in LocalAgentExecutor in
|
|
91
|
+
[#26548](https://github.com/google-gemini/gemini-cli/pull/26548)
|
|
92
|
+
- Changelog for v0.42.0-preview.2 in
|
|
93
|
+
[#26597](https://github.com/google-gemini/gemini-cli/pull/26597)
|
|
94
|
+
- skip broken test in
|
|
95
|
+
[#26705](https://github.com/google-gemini/gemini-cli/pull/26705)
|
|
96
|
+
- feat: export session to file and import via flag in
|
|
97
|
+
[#26514](https://github.com/google-gemini/gemini-cli/pull/26514)
|
|
98
|
+
- Feat: Add Machine Hostname to CLI interface in
|
|
99
|
+
[#25637](https://github.com/google-gemini/gemini-cli/pull/25637)
|
|
100
|
+
- docs(extensions): refactor releasing guide and add update mechanisms in
|
|
101
|
+
[#26595](https://github.com/google-gemini/gemini-cli/pull/26595)
|
|
102
|
+
- fix(ci): fix maintainer identification in lifecycle manager in
|
|
103
|
+
[#26706](https://github.com/google-gemini/gemini-cli/pull/26706)
|
|
104
|
+
- fix(ui): added quotes around session id in resume tip in
|
|
105
|
+
[#26669](https://github.com/google-gemini/gemini-cli/pull/26669)
|
|
106
|
+
- Changelog for v0.41.0 in
|
|
107
|
+
[#26670](https://github.com/google-gemini/gemini-cli/pull/26670)
|
|
108
|
+
- refactor(core): agent session protocol changes in
|
|
109
|
+
[#26661](https://github.com/google-gemini/gemini-cli/pull/26661)
|
|
110
|
+
- fix(context): implement loose boundary policy for gc backstop. in
|
|
111
|
+
[#26594](https://github.com/google-gemini/gemini-cli/pull/26594)
|
|
112
|
+
- fix(core): throw explicit error on dropped tool responses in
|
|
113
|
+
[#26668](https://github.com/google-gemini/gemini-cli/pull/26668)
|
|
114
|
+
- fix: resolve "function response turn must come immediately after function
|
|
115
|
+
call" error in
|
|
116
|
+
[#26691](https://github.com/google-gemini/gemini-cli/pull/26691)
|
|
117
|
+
- fix(core): resolve parallel tool call streaming ID collision in
|
|
118
|
+
[#26646](https://github.com/google-gemini/gemini-cli/pull/26646)
|
|
119
|
+
- feat(core): add LocalSubagentProtocol behind AgentProtocol in
|
|
120
|
+
[#25302](https://github.com/google-gemini/gemini-cli/pull/25302)
|
|
121
|
+
- fix(cli): remove noisy theme registration logs from terminal in
|
|
122
|
+
[#25858](https://github.com/google-gemini/gemini-cli/pull/25858)
|
|
123
|
+
- ci: implement codebase-aware effort level triage in
|
|
124
|
+
[#26666](https://github.com/google-gemini/gemini-cli/pull/26666)
|
|
125
|
+
- feat(acp/core): prefix tool call IDs with tool names to support tool rendering
|
|
126
|
+
in ACP compliant IDEs. in
|
|
127
|
+
[#26676](https://github.com/google-gemini/gemini-cli/pull/26676)
|
|
128
|
+
- fix(mcp): treat GET 404 as 405 in StreamableHTTPClientTransport in
|
|
129
|
+
[#24847](https://github.com/google-gemini/gemini-cli/pull/24847)
|
|
130
|
+
- feat(core): add RemoteSubagentProtocol behind AgentProtocol in
|
|
131
|
+
[#25303](https://github.com/google-gemini/gemini-cli/pull/25303)
|
|
132
|
+
- feat(context): Improvements to the snapshotter. in
|
|
133
|
+
[#26655](https://github.com/google-gemini/gemini-cli/pull/26655)
|
|
134
|
+
- fix(context): Change snapshotter model config. in
|
|
135
|
+
[#26745](https://github.com/google-gemini/gemini-cli/pull/26745)
|
|
136
|
+
- fix(cli): allow installing extensions from ssh repo in
|
|
137
|
+
[#26274](https://github.com/google-gemini/gemini-cli/pull/26274)
|
|
138
|
+
- fix(cli): prevent duplicate SessionStart systemMessage render in
|
|
139
|
+
[#25827](https://github.com/google-gemini/gemini-cli/pull/25827)
|
|
140
|
+
- fix(cli/acp): prevent infinite thought loop in ACP mode by disablig
|
|
141
|
+
nextSpeakerCheck in
|
|
142
|
+
[#26874](https://github.com/google-gemini/gemini-cli/pull/26874)
|
|
143
|
+
- fix(cli): use static tool name in confirmation prompt to avoid parsing errors
|
|
144
|
+
in [#26866](https://github.com/google-gemini/gemini-cli/pull/26866)
|
|
145
|
+
- fix(routing): Refactor tool turn handling for the conversation history in
|
|
146
|
+
NumericalClassifierStrategy to prevent 400 Bad Request in
|
|
147
|
+
[#26761](https://github.com/google-gemini/gemini-cli/pull/26761)
|
|
148
|
+
- fix(core): handle malformed projects.json in ProjectRegistry in
|
|
149
|
+
[#26885](https://github.com/google-gemini/gemini-cli/pull/26885)
|
|
150
|
+
- fix(ui): added a gutter width to the input prompt width calculation in
|
|
151
|
+
[#26882](https://github.com/google-gemini/gemini-cli/pull/26882)
|
|
152
|
+
- fix: prevent EISDIR crash when customIgnoreFilePaths contains directories
|
|
153
|
+
(#19868) in [#19898](https://github.com/google-gemini/gemini-cli/pull/19898)
|
|
154
|
+
- revert 6b9b778d821728427eea07b1b97ba07378137d0b in
|
|
155
|
+
[#26893](https://github.com/google-gemini/gemini-cli/pull/26893)
|
|
156
|
+
- Fix/vscode run current file ts in
|
|
157
|
+
[#22894](https://github.com/google-gemini/gemini-cli/pull/22894)
|
|
158
|
+
- Allow Enter to select session while in search mode in /resume in
|
|
159
|
+
[#21523](https://github.com/google-gemini/gemini-cli/pull/21523)
|
|
160
|
+
- fix(core): ignore .pak and .rpa game archive formats by default in
|
|
161
|
+
[#26884](https://github.com/google-gemini/gemini-cli/pull/26884)
|
|
162
|
+
- fix(cli): enable adk non-interactive session in
|
|
163
|
+
[#26895](https://github.com/google-gemini/gemini-cli/pull/26895)
|
|
164
|
+
- fix(cli): restore resume for legacy sessions in
|
|
165
|
+
[#26577](https://github.com/google-gemini/gemini-cli/pull/26577)
|
|
166
|
+
- fix: respect explicit model selection after Flash quota exhaustion (#26759) in
|
|
167
|
+
[#26872](https://github.com/google-gemini/gemini-cli/pull/26872)
|
|
168
|
+
- feat(context): Introduce adaptive token calculator to more accurately
|
|
169
|
+
calculate content sizes. in
|
|
170
|
+
[#26888](https://github.com/google-gemini/gemini-cli/pull/26888)
|
|
171
|
+
- chore: update checkout action configuration in workflows in
|
|
172
|
+
[#26897](https://github.com/google-gemini/gemini-cli/pull/26897)
|
|
173
|
+
- fix (telemetry): inject quota_project_id to prevent fallback to default oauth
|
|
174
|
+
client in [#26698](https://github.com/google-gemini/gemini-cli/pull/26698)
|
|
175
|
+
- Exclude extension context from skill extraction agent in
|
|
176
|
+
[#26879](https://github.com/google-gemini/gemini-cli/pull/26879)
|
|
177
|
+
- Enable NumericalRouter when using dynamic model configs in
|
|
178
|
+
[#26929](https://github.com/google-gemini/gemini-cli/pull/26929)
|
|
179
|
+
- ci: actively triage missing priority labels and intelligently clean up
|
|
180
|
+
conflicting labels in
|
|
181
|
+
[#26865](https://github.com/google-gemini/gemini-cli/pull/26865)
|
|
182
|
+
- refactor(core): introduce SubagentState enum for progress in
|
|
183
|
+
[#26934](https://github.com/google-gemini/gemini-cli/pull/26934)
|
|
184
|
+
- fix(ci): replace brittle --no-tag with explicit staging-tmp tag in
|
|
185
|
+
[#26940](https://github.com/google-gemini/gemini-cli/pull/26940)
|
|
186
|
+
- Incremental refactor repo agent towards skills-based composition in
|
|
187
|
+
[#26717](https://github.com/google-gemini/gemini-cli/pull/26717)
|
|
188
|
+
- fix(ui): fixed line wrap padding for selection lists in
|
|
189
|
+
[#26944](https://github.com/google-gemini/gemini-cli/pull/26944)
|
|
190
|
+
- fix(core): update read_file schema for v1 compatibility (#22183) in
|
|
191
|
+
[#26922](https://github.com/google-gemini/gemini-cli/pull/26922)
|
|
192
|
+
- fix(ci): configure git remote with token for authentication in
|
|
193
|
+
[#26949](https://github.com/google-gemini/gemini-cli/pull/26949)
|
|
243
194
|
|
|
244
195
|
**Full Changelog**:
|
|
245
|
-
https://github.com/google-gemini/gemini-cli/compare/v0.
|
|
196
|
+
https://github.com/google-gemini/gemini-cli/compare/v0.42.0-preview.2...v0.43.0-preview.0
|
|
@@ -29,11 +29,10 @@ You'll use Auto Memory when you want to:
|
|
|
29
29
|
avoid them.
|
|
30
30
|
- **Bootstrap a skills library** without writing every `SKILL.md` by hand.
|
|
31
31
|
|
|
32
|
-
Auto Memory complements
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
them without your approval.
|
|
32
|
+
Auto Memory complements direct memory-file editing. The agent can still persist
|
|
33
|
+
explicit user instructions by editing the appropriate Markdown memory file; Auto
|
|
34
|
+
Memory infers candidates from past sessions, writes reviewable patches or skill
|
|
35
|
+
drafts, and never applies them without your approval.
|
|
37
36
|
|
|
38
37
|
## Prerequisites
|
|
39
38
|
|
|
@@ -65,8 +65,6 @@ You can interact with the loaded context files by using the `/memory` command.
|
|
|
65
65
|
being provided to the model.
|
|
66
66
|
- **`/memory reload`**: Forces a re-scan and reload of all `GEMINI.md` files
|
|
67
67
|
from all configured locations.
|
|
68
|
-
- **`/memory add <text>`**: Appends your text to your global
|
|
69
|
-
`~/.gemini/GEMINI.md` file. This lets you add persistent memories on the fly.
|
|
70
68
|
|
|
71
69
|
## Modularize context with imports
|
|
72
70
|
|
|
@@ -138,7 +138,6 @@ These are the only allowed tools:
|
|
|
138
138
|
[`replace`](../tools/file-system.md#6-replace-edit) only allowed for `.md`
|
|
139
139
|
files in the `~/.gemini/tmp/<project>/<session-id>/plans/` directory or your
|
|
140
140
|
[custom plans directory](#custom-plan-directory-and-policies).
|
|
141
|
-
- **Memory:** [`save_memory`](../tools/memory.md)
|
|
142
141
|
- **Skills:** [`activate_skill`](../cli/skills.md) (allows loading specialized
|
|
143
142
|
instructions and resources in a read-only manner)
|
|
144
143
|
|
|
@@ -162,25 +162,24 @@ they appear in the UI.
|
|
|
162
162
|
|
|
163
163
|
### Experimental
|
|
164
164
|
|
|
165
|
-
| UI Label | Setting | Description
|
|
166
|
-
| ---------------------------------------------------- | ----------------------------------------------- |
|
|
167
|
-
| Gemma Models | `experimental.gemma` | Enable access to Gemma 4 models via Gemini API.
|
|
168
|
-
| Voice Mode | `experimental.voiceMode` | Enable experimental voice dictation and commands (/voice, /voice model).
|
|
169
|
-
| Voice Activation Mode | `experimental.voice.activationMode` | How to trigger voice recording with the Space key.
|
|
170
|
-
| Voice Transcription Backend | `experimental.voice.backend` | The backend to use for voice transcription. Note: When using the Gemini Live backend, voice recordings are sent to Google Cloud for transcription.
|
|
171
|
-
| Whisper Model | `experimental.voice.whisperModel` | The Whisper model to use for local transcription.
|
|
172
|
-
| Voice Stop Grace Period (ms) | `experimental.voice.stopGracePeriodMs` | How long to wait for final transcription after stopping recording.
|
|
173
|
-
| Enable Git Worktrees | `experimental.worktrees` | Enable automated Git worktree management for parallel work.
|
|
174
|
-
| Use OSC 52 Paste | `experimental.useOSC52Paste` | Use OSC 52 for pasting. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it).
|
|
175
|
-
| Use OSC 52 Copy | `experimental.useOSC52Copy` | Use OSC 52 for copying. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it).
|
|
176
|
-
| Model Steering | `experimental.modelSteering` | Enable model steering (user hints) to guide the model during tool execution.
|
|
177
|
-
| Direct Web Fetch | `experimental.directWebFetch` | Enable web fetch behavior that bypasses LLM summarization.
|
|
178
|
-
| Enable Gemma Model Router | `experimental.gemmaModelRouter.enabled` | Enable the Gemma Model Router (experimental). Requires a local endpoint serving Gemma via the Gemini API using LiteRT-LM shim.
|
|
179
|
-
| Auto-start LiteRT Server | `experimental.gemmaModelRouter.autoStartServer` | Automatically start the LiteRT-LM server when Gemini CLI starts and the Gemma router is enabled.
|
|
180
|
-
| Memory
|
|
181
|
-
|
|
|
182
|
-
|
|
|
183
|
-
| Enable Context Management | `experimental.contextManagement` | Enable logic for context management. | `false` |
|
|
165
|
+
| UI Label | Setting | Description | Default |
|
|
166
|
+
| ---------------------------------------------------- | ----------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------- |
|
|
167
|
+
| Gemma Models | `experimental.gemma` | Enable access to Gemma 4 models via Gemini API. | `true` |
|
|
168
|
+
| Voice Mode | `experimental.voiceMode` | Enable experimental voice dictation and commands (/voice, /voice model). | `false` |
|
|
169
|
+
| Voice Activation Mode | `experimental.voice.activationMode` | How to trigger voice recording with the Space key. | `"push-to-talk"` |
|
|
170
|
+
| Voice Transcription Backend | `experimental.voice.backend` | The backend to use for voice transcription. Note: When using the Gemini Live backend, voice recordings are sent to Google Cloud for transcription. | `"gemini-live"` |
|
|
171
|
+
| Whisper Model | `experimental.voice.whisperModel` | The Whisper model to use for local transcription. | `"ggml-base.en.bin"` |
|
|
172
|
+
| Voice Stop Grace Period (ms) | `experimental.voice.stopGracePeriodMs` | How long to wait for final transcription after stopping recording. | `4000` |
|
|
173
|
+
| Enable Git Worktrees | `experimental.worktrees` | Enable automated Git worktree management for parallel work. | `false` |
|
|
174
|
+
| Use OSC 52 Paste | `experimental.useOSC52Paste` | Use OSC 52 for pasting. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it). | `false` |
|
|
175
|
+
| Use OSC 52 Copy | `experimental.useOSC52Copy` | Use OSC 52 for copying. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it). | `false` |
|
|
176
|
+
| Model Steering | `experimental.modelSteering` | Enable model steering (user hints) to guide the model during tool execution. | `false` |
|
|
177
|
+
| Direct Web Fetch | `experimental.directWebFetch` | Enable web fetch behavior that bypasses LLM summarization. | `false` |
|
|
178
|
+
| Enable Gemma Model Router | `experimental.gemmaModelRouter.enabled` | Enable the Gemma Model Router (experimental). Requires a local endpoint serving Gemma via the Gemini API using LiteRT-LM shim. | `false` |
|
|
179
|
+
| Auto-start LiteRT Server | `experimental.gemmaModelRouter.autoStartServer` | Automatically start the LiteRT-LM server when Gemini CLI starts and the Gemma router is enabled. | `false` |
|
|
180
|
+
| Auto Memory | `experimental.autoMemory` | Automatically extract memory patches and skills from past sessions in the background. Every change is written as a unified diff `.patch` file under `<projectMemoryDir>/.inbox/<kind>/` and held for review in /memory inbox; nothing is applied until you approve it. | `false` |
|
|
181
|
+
| Use the generalist profile to manage agent contexts. | `experimental.generalistProfile` | Suitable for general coding and software development tasks. | `false` |
|
|
182
|
+
| Enable Context Management | `experimental.contextManagement` | Enable logic for context management. | `false` |
|
|
184
183
|
|
|
185
184
|
### Skills
|
|
186
185
|
|
|
@@ -71,8 +71,8 @@ Just tell the agent to remember something.
|
|
|
71
71
|
|
|
72
72
|
**Prompt:** `Remember that I prefer using 'const' over 'let' wherever possible.`
|
|
73
73
|
|
|
74
|
-
The agent will
|
|
75
|
-
|
|
74
|
+
The agent will edit the appropriate memory Markdown file, so the fact is loaded
|
|
75
|
+
in future sessions.
|
|
76
76
|
|
|
77
77
|
**Prompt:** `Save the fact that the staging server IP is 10.0.0.5.`
|
|
78
78
|
|
|
@@ -265,9 +265,6 @@ Slash commands provide meta-level control over the CLI itself.
|
|
|
265
265
|
- **Description:** Manage the AI's instructional context (hierarchical memory
|
|
266
266
|
loaded from `GEMINI.md` files).
|
|
267
267
|
- **Sub-commands:**
|
|
268
|
-
- **`add`**:
|
|
269
|
-
- **Description:** Adds the following text to the AI's memory. Usage:
|
|
270
|
-
`/memory add <text to remember>`
|
|
271
268
|
- **`list`**:
|
|
272
269
|
- **Description:** Lists the paths of the GEMINI.md files in use for
|
|
273
270
|
hierarchical memory.
|