Commit Graph

88 Commits

Author SHA1 Message Date
Allen Hutchison 53bf778497
feat: allow custom filename for context files (#654)
Co-authored-by: N. Taylor Mullen <ntaylormullen@google.com>
2025-05-31 12:49:28 -07:00
Scott Densmore 7012c86336
Fix/cli version unknown (#642) 2025-05-30 20:45:15 -07:00
Tommaso Sciortino 21fba832d1
Rename server->core (#638) 2025-05-30 18:25:47 -07:00
Jacob Richman 01768d7759
feat: add --show_memory_usage flag to display memory usage in status bar (#606) 2025-05-30 15:18:01 -07:00
Jacob Richman 6a1b94529b
Change Config to use named parameters. (#593) 2025-05-29 13:51:17 -07:00
sasha-gitg 3511e84dc3
fix: default to Gemini API if GEMINI_API_KEY is set and when GOOGLE_GENAI_USE_VERTEXAI is set to True (#566) 2025-05-27 10:00:07 -07:00
Allen Hutchison a008d81780
Refactor(server): Centralize GEMINI.md discovery logic in server (#498) 2025-05-23 08:53:22 -07:00
Allen Hutchison 0c192555bb
Fix: Prevent hang in large directories by using BFS for getFolderStru… (#470)
Co-authored-by: N. Taylor Mullen <ntaylormullen@google.com>
2025-05-22 10:47:21 -07:00
Olcan 3bf0304e31
ability to override core system prompt (via .gemini/system.md) and specify core tools via coreTools setting (e.g. coreTools:["ls", "GrepTool", ...]) ; added tests, but did not update docs for now (#413) 2025-05-17 19:45:16 -07:00
Olcan 76cf5e9fc1
rename env vars GEMINI_CODE_{MODEL,SANDBOX,SANDBOX_IMAGE} (#411) 2025-05-17 17:28:44 -07:00
Allen Hutchison 1bdec55fe1
feat: Implement CLI and model memory management (#371)
Co-authored-by: N. Taylor Mullen <ntaylormullen@google.com>
2025-05-16 16:36:50 -07:00
Olcan d9bd2b0e14
improved mcp support, including standard "mcpServers" setting with multiple named servers with command/args/env/cwd (#392) 2025-05-16 16:29:03 -07:00
sasha-gitg 609757f911
feat: Add support for Vertex AI and Vertex express mode (#380) 2025-05-16 08:06:43 -07:00
Olcan 6cd8f66a76
rename full_context as all_files (#366) 2025-05-15 11:44:56 -07:00
Olcan 4cc1dde625
refined cli (#365) 2025-05-15 11:38:33 -07:00
Allen Hutchison 89aa1cad41
Add UI memory indicator. (#348)
Co-authored-by: Gregory Shikhman <shikhman@google.com>
2025-05-14 15:19:45 -07:00
Allen Hutchison 1245fe4885
This commit introduces the hierarchical memory feature, allowing GEMI… (#327) 2025-05-14 12:37:17 -07:00
Taylor Mullen 8537aabba4 feat: Add User-Agent to API requests
This change introduces a User-Agent header to all API requests made by the Gemini CLI.

The User-Agent string includes the CLI version, Node.js version, operating system, and architecture. This will help in tracking usage and identifying potential issues.

Fixes https://b.corp.google.com/issues/416353675

Signed-off-by: Gemini
2025-05-11 14:33:58 -07:00
Taylor Mullen e9274b2ab2 feat: Update default Gemini model to gemini-2.5-pro-preview-05-06
Fixes https://b.corp.google.com/issues/416778280

Signed-off-by: Your Witty AI Assistant
2025-05-09 15:27:51 -07:00
olcan 9742f6e4a2 support for mcp tools 2025-05-05 17:10:45 -07:00
olcan 6b6eef5b80 support for discovered tools using project settings for discovery and call commands 2025-05-05 17:10:45 -07:00
Seth Troisi 415b757d4a
Remove passthroughCommands (#252) 2025-05-05 10:57:06 -07:00
Olcan b809953890
sandbox arg should not default to false but rather undefined (#244) 2025-05-02 10:05:53 -07:00
Olcan a7679db6e9
sandbox setting and argument (#243) 2025-05-02 08:15:46 -07:00
Brandon Keiji b27aae26c8
refactor: async-ify yargs (#236) 2025-05-01 01:00:53 +00:00
Allen Hutchison 8cf3e1611e
Adding a full_context command line argument. (#158)
* Adding a full_context command line argument.

* Update packages/cli/src/config/config.ts

Co-authored-by: N. Taylor Mullen <ntaylormullen@google.com>

* lint fix.

---------

Co-authored-by: N. Taylor Mullen <ntaylormullen@google.com>
2025-04-24 16:08:29 -07:00
Olcan aed42a726a
remove target_dir flag (#149) 2025-04-24 10:21:10 -07:00
Allen Hutchison 9bc9c6e6c5
Question flag (#125) 2025-04-22 18:32:03 -07:00
Olcan a7fba66832
env var to set default model, display model on lower right (#110) 2025-04-21 23:25:10 -07:00
Jaana Dogan d4614619b4
Remove dead comments (#90) 2025-04-21 13:06:46 -07:00
Juliette Love a76d9b4dcf
Adds shell command allowlist (#68)
* Wire through passthrough commands

* Add default passthrough commands

* Clean up config passing to useGeminiStream
2025-04-20 21:06:22 +01:00
Juliette Love a66ad2e2af
Simple debug mode for CLI side (#66)
* Adds debug mode config flag.

* Wire through debug lines

* Add debug mode logging example

* Run format

* Run format again
2025-04-20 20:20:40 +01:00
Evan Senter 3fce6cea27
Starting to modularize into separate cli / server packages. (#55)
* Starting to move a lot of code into packages/server

* More of the massive refactor, builds and runs, some issues though.

* Fixing outstanding issue with double messages.

* Fixing a minor UI issue.

* Fixing the build post-merge.

* Running formatting.

* Addressing comments.
2025-04-19 19:45:42 +01:00
Jaana Dogan 65e8e3ed1f
Show error when GEMINI_API_KEY is not set (#52)
Also fix the bug where the API key is used accidentally as the model name.
2025-04-18 19:26:16 -07:00
Tyler 4354458cad
Add apache2 SPDX headers to all source files (#48) 2025-04-18 17:44:24 -07:00
Taylor Mullen 383b917784 Run `npm run format`
- This has the entirety of the changes.

Part of https://b.corp.google.com/issues/411720532
2025-04-18 18:10:57 -04:00
Jaana Dogan 328846c6e3
Remove extra args from config (#27)
We don't have a use case for them yet.
2025-04-18 11:26:39 -07:00
Jaana Dogan 3afaa8033b
Introduce a config module to manage configuration (#22)
* Introduce a config module to manage configuration

* Remove public modifier
2025-04-18 11:12:18 -07:00