Commit Graph

15 Commits

Author SHA1 Message Date
AI Christianson 94d655ce91 skip binary files; update deps 2025-02-25 18:32:29 -05:00
AI Christianson 04913bdaf3 fix bug where model selection on anthropic was always using default 2025-02-24 14:35:09 -05:00
AI Christianson ba92f49a91 fix bug where we sent reasoning_effort to models that do not support it. fixes #91 2025-02-17 19:08:06 -05:00
Ariel Frischer e6ba8f5dff
Merge pull request #95 from ariel-frischer/test-cmd-args
feat: add `--test-cmd-timeout` option to specify timeout for test command
2025-02-17 15:25:09 -08:00
AI Christianson 7c3c616531 use base latency in programmer tool 2025-02-17 18:21:49 -05:00
Ariel Frischer 685d098f21 feat(docusaurus): add Vercel analytics plugin to enhance performance tracking
feat(models_params.py): add DEFAULT_BASE_LATENCY constant and integrate it into model parameters for latency management
fix(package.json): add @docusaurus/plugin-vercel-analytics dependency to support new analytics feature
2025-02-17 15:19:01 -08:00
AI Christianson e8e4dac038 add base latency model param 2025-02-17 18:11:33 -05:00
Ariel Frischer 581dc4b761 feat: add `--test-cmd-timeout` option to specify timeout for test command execution
This change introduces a new command-line option `--test-cmd-timeout` to allow users to set a timeout for the execution of test commands. The default timeout is set to 300 seconds. This enhancement provides users with more control over the execution time of their test commands, helping to prevent indefinite hangs during testing.

Additionally, the codebase has been updated to utilize this new timeout setting in relevant areas, ensuring consistent behavior across the application.
2025-02-17 11:03:19 -08:00
AI Christianson 905ed2c8fc improve expert model auto detection 2025-02-12 15:55:47 -05:00
AI Christianson a1371fc7e0 support default temp on a per-model basis; show status panel 2025-02-12 13:38:52 -05:00
AI Christianson 53ccc46392 Add model params for o1 and o3-mini. 2025-02-02 18:48:41 -05:00
Ariel Frischer 1cc5b8e16c refactor: clean up imports and improve code formatting for better readability
fix: ensure proper error handling and logging in WebSocket connections
feat: enhance WebSocket server to handle streaming and error messages more effectively
chore: update model parameters and configurations for better performance and maintainability
test: improve test coverage for model token limits and agent creation logic
2025-02-01 13:00:15 -08:00
AI Christianson e3414890ff Add logic to handle whether a model supports temperature or not. 2025-01-31 17:04:52 -05:00
AI Christianson 1c463fca17 Add supports_temperature model param. 2025-01-31 16:35:43 -05:00
AI Christianson f7e02fc98e Refactor models_tokens to be models_params so we can track multiple parameters on a per-model basis. 2025-01-31 16:05:44 -05:00