avtc
1e5783d051
LM studio reasoning support (thinking block) ( #3719 )
...
lmstudio reasoning support (thinking block)
Similar to ollama implementation in #1080
2025-05-19 12:55:56 -07:00
pugazhendhi-m
d851586042
Adds refresh models button for Unbound provider ( #3663 )
...
* Adds refresh models button for Unbound provider
* Adds changeset
* Optimizes code to prevent memory leak, add error messages
* Adds unbound messages to all supported languages
---------
Co-authored-by: Pugazhendhi <pugazhendhi@unboundsecurity.ai>
2025-05-17 18:09:39 -07:00
Canyon Robins
7c1185ed33
[Condense] Condense messages with an LLM rather than truncating ( #3582 )
...
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-05-14 16:44:01 -04:00
Daniel Trugman
a14b655590
Requesty: Only report final usage ( #3542 )
2025-05-13 07:24:28 -04:00
Daniel
9ffdc7879e
Use the provider-specific model info for the OpenRouter provider ( #3430 )
2025-05-12 18:23:32 -07:00
Chris Estreich
20fab97b4d
Gemini implicit caching ( #3515 )
2025-05-12 14:16:27 -07:00
John Richmond
8cb5c4e9e3
Restore profile management work + fix #3434 ( #3449 )
...
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-05-12 15:47:09 -04:00
Matt Rubens
730d037a12
Revert "Improve provider profile management in the external API ( #3386 )" ( #3440 )
2025-05-10 08:27:37 -04:00
Chris Estreich
c21aa230e3
Get rid of ApiConfiguration type alias, rename ApiConfigMeta to ProviderSettingsEntry ( #3380 )
2025-05-08 23:52:18 -07:00
Daniel
83bf86f637
Fix not being able to use specific providers on Openrouter ( #3354 )
2025-05-08 22:50:23 -04:00
Shariq Riaz
037a62bf67
Fix: Enforce provider selection in OpenRouter by using 'only' parameter and disabling fallbacks ( #3338 )
2025-05-08 09:50:06 -07:00
John Richmond
0bbd3fd1df
Add LiteLLM provider ( #3242 )
...
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-05-07 14:53:21 -04:00
Chris Estreich
b0757c2d05
Enable Gemini prompt caching by default ( #3225 )
2025-05-06 09:56:57 -07:00
Daniel Trugman
ce8fbbdafa
Requesty provider fixes ( #3193 )
...
Co-authored-by: Chris Estreich <cestreich@gmail.com>
2025-05-05 20:49:11 -07:00
Chris Estreich
da6c50bf10
Organize provider settings into separate components ( #3196 )
2025-05-05 15:53:01 -07:00
Shariq Riaz
883be32b1a
feat: Add Groq and Chutes API providers ( #3034 )
...
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: Chris Estreich <cestreich@gmail.com>
2025-05-05 15:16:27 -07:00
Chris Estreich
98adb04f98
Gemini caching tweaks ( #3142 )
2025-05-03 07:55:35 -07:00
Chris Estreich
06d8dd2bcf
Gemini caching fixes ( #3096 )
2025-05-02 16:36:22 -07:00
Matt Rubens
a356d70669
Customizable headers for the OpenAI-compatible provider ( #3056 )
...
* Customizable headers for the OpenAI-compatible provider
* PR feedback
* Fix migration
* Update webview-ui/src/components/settings/ApiOptions.tsx
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-05-01 23:30:57 -04:00
gongzhongqiang
8c428b5b63
feat(openai): Add Config Option to Overwrite OpenAI's API Base ( #3066 )
...
* feat(openai): Add Config Option to Overwrite OpenAI's API Base
* feat(openai): Add option to use custom base URL for OpenAI native API
2025-05-01 10:23:18 -04:00
Chris Estreich
7863303aac
Fall back to execa if VSCode terminal integration fails ( #3049 )
2025-04-29 21:10:41 -07:00
Chris Estreich
65cb9244ee
Count tokens worker ( #3037 )
...
* Count tokens worker
* Appease knip
2025-04-29 12:29:25 -07:00
Ash R
a3d8c0e3f6
feat: vertex/gemini prompt caching ( #2996 )
2025-04-28 15:11:35 -07:00
Ryan Pfister
2075f26f18
feat: Add Reasoning Effort setting for OpenAI Compatible provider ( #2906 )
2025-04-28 13:36:47 -07:00
Chris Estreich
1924e10e72
Fix all linter errors (and fix the lint scripts too) ( #2958 )
2025-04-26 09:45:26 -07:00
Chris Estreich
c8b5cdf7b2
Omit reasoning params for non-reasoning models ( #2932 )
2025-04-25 15:24:03 -07:00
Chris Estreich
cb29e9d56f
Remove ModelInfo objects from settings ( #2939 )
2025-04-25 15:23:25 -07:00
Chris Estreich
06db547308
Use a WASM-based tiktoken implementation ( #2859 )
...
* Use a WASM-based tiktoken implementation
* Clean up imports
2025-04-25 10:32:35 -07:00
pugazhendhi-m
7e76736e13
Updates default model for Unbound ( #2944 )
...
* Updates default model for Unbound
* Adds changeset
---------
Co-authored-by: Pugazhendhi <pugazhendhi@unboundsecurity.ai>
2025-04-25 07:36:25 -04:00
Chris Estreich
0dfbae64f3
Allow users to toggle Gemini caching on / off for OpenRouter ( #2927 )
2025-04-24 16:34:22 -07:00
Chris Estreich
a3f1a3f3ad
Gemini caching improvements ( #2925 )
2025-04-24 14:20:09 -07:00
Chris Estreich
b75379bed3
Improve OpenRouter model fetching ( #2922 )
2025-04-24 12:29:36 -07:00
Chris Estreich
fb91836203
Revert Gemini caching, fix OR supports cache issue ( #2918 )
2025-04-24 09:15:56 -07:00
Matt Rubens
a53f604e3a
Disable OpenRouter Gemini caching for now ( #2890 )
2025-04-23 16:46:52 -04:00
Chris Estreich
a08461a655
Gemini prompt caching ( #2827 )
2025-04-23 11:35:50 -07:00
Chris Estreich
a9ca17717c
OpenRouter Gemini caching ( #2847 )
...
* OpenRouter Gemini caching
* Fix tests
* Remove unsupported models
* Clean up the task header a bit
* Update src/api/providers/openrouter.ts
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* Remove model that doesn't seem to work
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-04-23 09:45:57 -04:00
mlopezr
e53d299acf
Allow Amazon Bedrock Marketplace ARNs ( #2874 )
...
* Update validate.ts
Allow ARNs from Bedrock Marketplace, which are different because models are deployed using SageMaker Inference behind the scenes.
* Update bedrock.ts
Allow ARNs from Bedrock Marketplace, which are different because models are deployed using SageMaker Inference behind the scenes.
2025-04-23 09:36:50 -04:00
Dominik Oswald
844753e0d9
Remove unnecessary cost calculation from vscode-lm.ts ( #2875 )
...
* feat: Removed unnecessary cost calculation
* Update vscode-lm.ts
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-04-23 09:34:32 -04:00
Wojciech Kordalski
74faacd69d
FakeAI "controller" object must not be copied ( #2463 )
...
The FakeAI object passed by the user must be exactly the same object
that is passed to FakeAIHandler via API configuration.
Unfortunatelly, as the VSCode global state is used as configuration
storage, we lose this property (VSCode global state creates copies of
the object). Also the class of the stored object is lost, so methods
of the object are unavailable.
Therefore, we store the original objects in global variable and
use ID field of FakeAI object to identify the original object.
2025-04-23 01:42:06 -07:00
Alfredo Medrano
3a5913ffca
Bugfix/fix vscodellm model information ( #2832 )
...
* feat: initialize VS Code Language Model client in constructor
* feat: add VS Code LLM models and configuration
* feat: integrate VS Code LLM models into API configuration normalization
* Fix tests
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-04-23 03:05:47 -04:00
Daniel Trugman
b955dbc1fc
Requesty models behind api key ( #2813 )
...
* Don't fetch Requesty models on startup, only when opening settings
* Provide api key when fetching models
2025-04-21 11:56:02 -04:00
Chris Estreich
c10600e354
Pass baseURL to Gemini API if googleGeminiBaseUrl is set ( #2776 )
2025-04-18 19:25:42 -07:00
Chris Estreich
5abea50cf1
Support Gemini 2.5 Flash thinking ( #2752 )
2025-04-18 12:26:17 -07:00
Smartsheet-JB-Brown
b077267b4a
fixes image support in bedrock. regression from prompt cache implementation ( #2723 )
...
fixes image support in bedrock. regression created during prompt caching implementation
2025-04-17 15:25:11 -07:00
Matt Rubens
43668e0429
Add support for different reasoning effort ( #2692 )
2025-04-16 14:16:51 -04:00
Matt Rubens
37f7d83792
Add xAI provider ( #2667 )
...
* Add xAI provider
* Add model reasoning effort
* DRY this up
* Handle undefined delta
* Cleanup getModel to fix test
* Add missing translations
* Small type cleanup
* Support temperature
---------
Co-authored-by: cte <cestreich@gmail.com>
2025-04-15 22:16:52 -04:00
Chris Estreich
e7a57ea774
Expose reasoning effort option for reasoning models on OpenRouter ( #2483 )
...
* Specify reasoning effort for OpenRouter reasoning models
* Add ReasoningEffort type
* Fix ReasoningEffort props
* Remove copypasta
* Set reasoning effort for Grok 3 Mini
* Use translations
* Add translations
* Remove this check
2025-04-15 13:51:52 -07:00
Matt Rubens
a64cab92dc
Fix openai cache tracking and cost estimates ( #2616 )
...
* fix(api): update cacheReadsPrice for OpenAI GPT-4.1 models (#2887 )
Set correct cacheReadsPrice (cached input price) for gpt-4.1, gpt-4.1 mini, and gpt-4.1 nano based on official OpenAI pricing. No changes to cacheWritesPrice as per current OpenAI documentation. This ensures prompt caching costs are accurately reflected for these models in cost calculations.
* Update more OpenAI cache prices
* Track cache tokens and cost correctly for OpenAI
* Update tests
---------
Co-authored-by: monotykamary <tom81094@gmail.com>
2025-04-14 22:55:06 -04:00
Matt Rubens
ab7ca17f29
Fix test ( #2607 )
2025-04-14 13:27:33 -04:00
vagadiya
628d232f9f
Fix AWS token expiry issue when cached token expires when using AWS Profile for Bedrock ( #2469 ) ( #2530 )
...
Fix AWS token expiry issue when cached token expires and using AWS Profile (#2469 )
2025-04-12 22:23:48 -04:00
